sourceactiveSources

Raw Papers Batch Ingest

This batch source note catalogs 185 raw papers markdown sources currently present under vault/01-Raw-Sources/papers/. The raw files remain immutable; this note is the durable ingest handle used by wiki pages, claims, and research questions.

Batch Analysis

Source count: 185
Dominant operation: batch ingest from raw captures into wiki synthesis.
Evidence quality: mixed. Treat papers and standards as stronger evidence than news and vendor reports; treat collection manifests as routing aids, not direct evidence.
Citation status: raw paper captures include bibliographic metadata when available, but canonical DOI/arXiv verification should be refreshed for sources promoted into claims or reports.

Paper Lookup Verification

The batch ingest used existing raw capture metadata to identify titles, source kinds, publication dates, tags, URLs, and summaries. Canonical DOI/arXiv/OpenAlex/Semantic Scholar verification should be refreshed with paper-lookup for any individual paper that is promoted into a stable claim, report, or formal literature review.

Citation Record

This note is a batch-level citation handle for the current raw paper corpus. Individual paper citations remain in the raw capture files and should be normalized with citation-management before publication-grade reuse.

Evidence Quality

The paper corpus is strong for topic discovery and benchmark mapping, but mixed for claim stabilization. Benchmark papers, surveys, and peer-reviewed work should be separated from collection manifests, preliminary preprints, and unverified capture notes before assigning high confidence to claims.

Scholar Evaluation

At batch level, the corpus shows broad coverage of agent security, prompt injection, memory poisoning, RAG security, MCP/protocol security, AI SOC, and benchmark design. Source-specific scholar evaluation remains required before treating a paper as decisive evidence.

Key Claims

Agentic AI security extends beyond prompt safety into tools, memory, protocols, authorization, and runtime monitoring.
Prompt injection, memory poisoning, RAG poisoning, and tool poisoning recur as dominant attack families.
Security benchmarks are abundant, but their deployment validity remains an unresolved research question.

Contradictions Or Caveats

Many papers propose defenses, but the source captures do not yet establish cross-model or production generalization.
Some benchmark claims may be sensitive to task design, model choice, contamination, and scoring methodology.
Collection manifests are routing aids rather than direct evidence.

Follow-Up Hypotheses

Defense methods that bind authority to memory provenance may reduce persistent-agent poisoning without destroying utility.
Runtime gateway controls may work best when paired with action-scoped identity and audit evidence.
Benchmarks that include realistic tools, secrets, logs, and failure recovery may better predict deployment risk.

Candidate Research Questions

Source Catalog

Title	Kind	Date	Tags	Raw
Prompt Injection in Automated Résumé Screening with Large Language Models: Single and Multi-Injectio	paper	2026-06-25	Jane Yi Jiang, Jiannan Xu, Preet Baxi, Stefanus Jasin, decision-integrity, hiring-workflow	raw
AI Security Paper Collection 2026-06-25	collection_manifest	2026-06-25	agent-security, ai-for-security, ai-security, collection-manifest, jailbreak, papers	raw
What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics	paper	2026-06-24	ai-security, detection, guardrails, jailbreak, mechanistic-interpretability	raw
Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution	paper	2026-06-24	ai-security, attribution, provenance, rag, retrieval-poisoning	raw
Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future	paper	2026-06-24	ai-security, defense, privacy, rag, survey, threat-model	raw
How Reliable Is Your Jailbreak Judge? Calibration and Adversarial Robustness of Automated ASR Scorin	paper	2026-06-24	ai-security, asr, calibration, evaluation, jailbreak, llm-judge	raw
AI Snitches Get Glitches: Towards Evading Agentic Surveillance	paper	2026-06-24	adversarial, agentic-ai, ai-security, monitoring, surveillance-evasion	raw
Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Ma	paper	2026-06-23	agent-memory, ai-security, formal-methods, memory-poisoning, provenance	raw
REALM: A Unified Red-Teaming Benchmark for Physical-World VLMs	paper	2026-06-23	ai-security, benchmark, multimodal-security, red-teaming, vlm	raw
Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Comprom	paper	2026-06-23	ai-security, multi-agent-systems, privacy, rag, semantic-rewriting	raw
Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents	paper	2026-06-23	ai-for-security, ai-security, knowledge-poisoning, playbooks, soc-agent	raw
PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation	paper	2026-06-23	ai-security, evaluation, jailbreak, self-evolving, text-to-image	raw
When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Pr	paper	2026-06-22	ai-security, computer-use-agent, evaluation, hidden-state-probes, indirect-prompt-injection, multimodal-agent	raw
Self-Evolving Agent Rollout and Experience Buffer Collection	collection_manifest	2026-06-22	attack-surface, collection, experience-memory, rollout-buffer, self-evolving-agent	raw
RAVEN: Agentic RAG for Automated Vulnerability Repair	paper	2026-06-22	agentic-rag, ai-for-security, software-security, vulnerability-repair	raw
GIF: Locally Sound Geometric Information Flow Control for LLMs	paper	2026-06-22	ai-security, data-leakage, formal-methods, information-flow-control, llm	raw
Detecting Malicious Agent Skills in the Wild using Attention	paper	2026-06-22	agent-skills, ai-security, detection, malicious-skills, supply-chain	raw
Confidently Wrong: Severity-Aware Calibration of Prompt-Injection Detectors under Attack Shift	paper	2026-06-22	ai-security, detector-calibration, evaluation, prompt-injection, robustness	raw
AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent	paper	2026-06-22	ai-security, coding-agent, interpretability, multi-turn-agent, safety-steering	raw
Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents	paper	2026-06-20	agent-memory, ai-security, context-compression, llm-agent, prompt-injection	raw
AgentRiskBOM: A Risk-Scoping Security Bill of Materials for Agentic AI Systems	paper	2026-06-20	agentic-ai, ai-security, governance, risk-management, sbom	raw
Agent-Assisted Side-Channel Attacks on Non-Prefix KV Cache in RAG	paper	2026-06-20	agent-assisted-attack, ai-security, kv-cache, rag, side-channel	raw
\"What Happens Locally, Leaks Globally\": Detecting Privacy Leakage Risks in MCP Servers	paper	2026-06-19	agent-security, ai-security, mcp, privacy-leakage, static-analysis, tool-security	raw
Scalable Hierarchical Attention Transformers for Multi-Turn Jailbreak Detection in Long Conversation	paper	2026-06-19	ai-security, detection, jailbreak, long-context, multi-turn	raw
OTTER: A Red-Teaming System for Toxicity-Evading Jailbreak Prompt Optimization	paper	2026-06-19	ai-security, jailbreak, prompt-optimization, red-teaming, safety-evaluation	raw
Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers	paper	2026-06-19	ai-for-security, cyber-deception, honeypot, llm-attackers, threat-intelligence	raw
AgenticOS: An Intent-Oriented Secure Operating System Architecture for Autonomous AI Agents	paper	2026-06-19	agentic-ai, ai-security, intent, runtime-security, secure-os	raw
Efficient and Sound Probabilistic Verification for AI Agents	paper	2026-06-18	Alaia Solko-Breslin, Krishnamurthy Dvijotham, Mihai Christodorescu, Pramod Kaushik Mudrakarta, Somesh Jha, datalog	raw
A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots	paper	2026-06-18	ai-security, chatbot-security, defense, prompt-injection, rag	raw
Ghost Vectors: Soft-Deleted Embeddings Remain Reconstructible in HNSW Vector Databases	paper	2026-06-17	ai-security, data-deletion, embeddings, privacy, rag, vector-database	raw
From Privacy to Workflow Integrity: Communication-Graph Metadata in Autonomous Agent Interoperabilit	paper	2026-06-17	a2a, ai-security, mcp, metadata-leakage, multi-agent-systems, workflow-integrity	raw
Code-Augur: Agentic Vulnerability Detection via Specification Inference	paper	2026-06-17	agentic-ai, ai-for-security, software-security, specification-inference, vulnerability-detection	raw
SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents	paper	2026-06-16	Chao Xu, Hanting Chen, Haocheng Mei, Mengyu Zheng, Xinghao Chen, Ye Yuan	raw
Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems	paper	2026-06-16	ai-security, knowledge-injection, poisoning, rag, retriever-editing	raw
An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios	paper	2026-06-15	agent-security, ai-security, data-leakage, privacy, tool-using-agent	raw
TrustedARI: Towards Trust-Native Agentic Routing Infrastructure for Agentic AI	paper	2026-06-14	agentic-ai, ai-security, multi-agent-systems, routing, trust-infrastructure	raw
One Goal, Many Commands: Characterizing Denylist Fragility in AI Agents	paper	2026-06-14	agent-security, ai-security, denylist, policy-enforcement, tool-use	raw
Let Them Steal: Trapping Large Language Model Extraction Attacks with Knowledge Honeypot	paper	2026-06-14	ai-security, defense, honeypot, llm, model-extraction	raw
AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems	paper	2026-06-14	ai-evolved-systems, ai-security, self-evolving-ai, testing, weakness-discovery	raw
Same-Origin Policy for Agentic Browsers	paper	2026-06-12	agentic-browser, ai-security, prompt-injection, same-origin-policy, web-security	raw
Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs	paper	2026-06-12	ai-security, context-poisoning, mcp, multi-agent-control, prompt-injection, rollback	raw
AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges	paper	2026-06-12	ai-for-security, benchmark, cyber-capability, cyber-range, frontier-ai	raw
SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems	paper	2026-06-11	agent-memory, ai-security, certified-defense, memory-poisoning, persistent-agents	raw
PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections	paper	2026-06-10	Ash Fox, George Lee, Jiliang Tang, Lesly Miculicich, Long T. Le, Pengfei He	raw
Influence Factors on RAG Poisoning	paper	2026-06-10	ai-security, evaluation, poisoning, rag, retrieval	raw
Agents All the Way Down; A Methodology for Building Custom AI Agents from Substrate to Production	paper	2026-06-10	agent-methodology, agentic-ai, ai-technology, audit-trail, custom-agents, security-boundaries	raw
When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipeline	paper	2026-06-09	ai-security, chunking, corpus-poisoning, rag, reranking, retrieval	raw
Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution	paper	2026-06-09	co-evolution, curriculum, failure-history, rollout-trajectories, self-evolving-agent	raw
Assessing Automated Prompt Injection Attacks in Agentic Environments	paper	2026-06-09	David Hofer, Edoardo Debenedetti, Florian Tram챔r, agent-security, agentdojo, benchmark	raw
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environment	paper	2026-06-09	agent-security, ai-security, benchmark, evaluation, executable-environment	raw
The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context	paper	2026-06-08	ai-security, context-injection, prompt-injection, rag, recommendation	raw
Document-Authored Control-Signal Impersonation: A Low-Cost Indirect Prompt Attack on RAG Safety Boun	paper	2026-06-08	ai-security, control-signal, indirect-prompt-injection, rag, safety-boundary	raw
RAILS: Verification-Native Clearing For Agentic Commerce	paper	2026-06-07	agent-integrity, agentic-commerce, ai-security, non-human-identity, settlement-risk, verification	raw
GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines	paper	2026-06-07	Ilia Shumailov, Jafar Isbarov, Murat Kantarcioglu, Umid Suleymanov, benchmark, ci-cd	raw
Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems	paper	2026-06-07	Gao Cong, Guoliang Li, Haoyang Li, Kuncan Wang, Peizhuo Lv, Wei Dong	raw
OpenAgenet / OAN Yellow Paper: Technical Architecture for Trust-Governed Resource Identity and Disco	paper	2026-06-05	a2a, agent-identity, ai-security, mcp, resource-discovery, skills	raw
ZERO-APT: A Closed-Loop Adversarial Framework for LLM-Driven Automated Penetration Testing under Int	paper	2026-06-04	Anlan Zheng, Tiantian Zhu, ai-for-security, auditability, cyber-benchmark, defender-in-the-loop	raw
What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in Agentic Syst	paper	2026-06-03	Liya Su, Suchen Liu, Tianyun Liu, Tingwen Liu, Yingjie Zhang, Yuanbo Xie	raw
NLLog: Lightweight, Explainable SOC Anomaly Detection via Log-to-Language Rewriting	preprint	2026-06-03	ai-for-security, ai-soc, anomaly-detection, explainability, log-analysis	raw
From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents	paper	2026-06-03	Aditi Jain, Pritam Dash, Tanmay Shah, Tongyu Ge, Zhiwei Shang, agent-memory	raw
CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities	paper	2026-06-03	Alexander Cheung, Chenguang Wang, Dawn Song, Dongwei Jiang, Francisco De La Riega, Gabriel Han	raw
AI Model Extraction Attacks: Bypassing Single-Client Assumptions in Defenses	paper	2026-06-02	Gustavo S찼nchez, Johannes F. Loevenich, Laurin Holz, Maxime Schwarzer, Roberto Rigolin F. Lopes, Thies M철hlenhof	raw
An Embarrassingly Simple Detector for Model Extraction Attacks in LLM APIs	paper	2026-06	detection, latest-research, llm-api-security, model-extraction, security-for-ai	raw
SS-ZKR: Spatial-Semantic Zero-Knowledge Routing for Privacy-Preserving Multi-Agent Collaboration	paper	2026-05-31	a2a, ai-security, mcp, multi-agent-systems, privacy, routing	raw
Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems	paper	2026-05-30	Ismail Hossain, Nan Jiang, Sai Puppala, Sajedul Talukder, Zhuoran Lu, agent-skills	raw
Poison with Style: A Practical Poisoning Attack on Code Large Language Models	paper	2026-05-26	Issa Khalil, Khang Tran, Md Rizwan Parvez, NhatHai Phan, Ting Yu, Yazan Boshmaf	raw
MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning	paper	2026-05-24	accumulated-experience, memory-poisoning, persistent-state, tool-hijacking, tool-selection	raw
SkillOpt: Executive Strategy for Self-Evolving Agent Skills	paper	2026-05-22	agent-skills, microsoft, self-evolving-agents, skillopt, text-space-optimization	raw
MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly D	paper	2026-05-22	anomaly-detection, causal-attribution, counterfactual-replay, memory-audit, poisoning	raw
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills	paper	2026-05-22	agent-skills, microsoft, model-generated-skills, self-evolving-agents, skilllens	raw
Self-Evolving Multi-Agent Systems via Decentralized Memory	paper	2026-05-21	decentralized-memory, llm-as-a-judge, mas-misevolution-propagation, multi-agent, persistent-memory, self-evolving-agents	raw
LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection	paper	2026-05-18	benchmark, executable-harm, indirect-prompt-injection, security-for-ai, virtual-machine	raw
AI Agents May Always Fall for Prompt Injections	paper	2026-05-17	contextual-integrity, defense-limitations, information-flow, prompt-injection, security-for-ai	raw
State Contamination in Memory-Augmented LLM Agents	paper	2026-05-16	mas-misevolution-propagation, memory-laundering, memory-poisoning, multi-agent-rollouts, persistent-state, state-contamination	raw
MemLineage: Lineage-Guided Enforcement for LLM Agent Memory	paper	2026-05-14	derivation-dag, memory-lineage, merkle-log, provenance, sensitive-action-gate	raw
DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agen	paper	2026-05-06	agent-security, benchmark, prompt-injection, red-teaming, security-for-ai, skill-injection	raw
Authorization Propagation in Multi-Agent AI Systems: Identity Governance as Infrastructure	paper	2026-05-06	authorization, delegation, identity-governance, multi-agent-systems, security-for-ai	raw
Defending LLM Agents Against Context-Aware Prompt Injection	paper	2026-05-05	agents, ai-security, context-aware-attacks, defenses, prompt-injection	raw
You Live More Than Once: Towards Hierarchical Skill Meta-Evolving	paper	2026-05	agent-skills, meta-evolving, self-evolving-agents, skill-evolving, test-time-learning	raw
Toward Autonomous SOC Operations: End-to-End LLM Framework for Threat Detection, Query Generation, a	paper	2026-04-30	Akramul Azim, Md Hasan Saju, ai-for-security, ai-soc, autonomous-soc, query-generation	raw
OpenSOC-AI: Democratizing Security Operations with Parameter Efficient LLM Log Analysis	preprint	2026-04-29	ai-for-security, ai-soc, llm, log-analysis, lora, smbs	raw
AgentSOC: A Multi-Layer Agentic AI Framework for Security Operations Automation	paper	2026-04-22	Joyjit Roy, Samaresh Kumar Singh, agentic-soc, ai-for-security, ai-soc, incident-response	raw
MemEvoBench: Benchmarking Safety Risks from Memory Misevolution in LLM Agents	paper	2026-04-17	benchmark, biased-feedback, long-horizon-safety, memory-misevolution, noisy-tools	raw
CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution	paper	2026-04-17	agent-data-coevolution, forgetting, rollout-trajectories, self-evolving-agent, uncertainty	raw
SIR-Bench: Evaluating Investigation Depth in Security Incident Response Agents	paper	2026-04-13	Bonan Zheng, Cristian Leo, Daniel Begimher, Jack Huang, Pat Gaw, ai-for-security	raw
Like a Hammer, It Can Build, It Can Break: Large Language Model Uses, Perceptions, and Adoption in C	paper	2026-04-11	Aditi Ganapathi, Chih-Yi Huang, Gail-Joon Ahn, Jaron Mink, Kashyap Thimmaraju, Souradip Nath	raw
LanG -- A Governance-Aware Agentic AI Platform for Unified Security Operations	preprint	2026-04-07	agentic-ai, ai-for-security, ai-soc, governance, human-in-the-loop, mcp	raw
Security risk management in the digital enterprise: enhancing cyber defense with large language mode	journal_paper	2026-04-06	Abdulrahman Alojail, Samir A. E. Kahouf, Shaymaa Sorour, Shorouk El-Deep, ai-for-security, ai-soc	raw
Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool P	paper	2026-03-23	Amin Milani Fard, Charoes Huang, Ngoc Phu Tran, Xin Huang, mcp-security, security-for-ai	raw
Memory poisoning and secure multi-agent systems	paper	2026-03-20	episodic-memory, mas-misevolution-propagation, memory-poisoning, multi-agent, secure-mas, semantic-memory	raw
Retrieval-Augmented LLMs for Security Incident Analysis	paper	2026-03-18	Aditya Vikram Singh, Alex Fitts, Alina Oprea, Dirk Van Bruggen, Edward Koh, Harsh Mamania	raw
SAGE: Multi-Agent Self-Evolution for LLM Reasoning	paper	2026-03-16	critic, curriculum-pool, multi-agent, self-evolving-agent, verifier	raw
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Compe	paper	2026-03-16	benchmark, computer-use, concealment, indirect-prompt-injection, red-teaming, security-for-ai	raw
Before You Hand Over the Wheel: Evaluating LLMs for Security Incident Analysis	paper	2026-03-06	Adrian Taylor, Grant Vandenberghe, Madeena Sultana, Sourov Jajodia, Suryadipta Majumdar, agentic-evaluation	raw
From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration	paper	2026-03-04	error-cascade, genealogy-graph, llm-mas, mas-misevolution-propagation, multi-agent, propagation	raw
ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities	paper	2026-03	ai-for-security, benchmark, llm-agents, vulnerability-patching, zero-day	raw
The Attack and Defense Landscape of Agentic AI	paper	2026-03	agent-security, attack-landscape, defense-landscape, open-challenges, security-for-ai	raw
Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios	paper	2026-03	ai-for-security, benchmark, cyber-range, llm-agents, multi-step-attack, risk-evaluation	raw
From Secure Agentic AI to Secure Agentic Web: Challenges, Threats, and Future Directions	paper	2026-03	agent-security, agentic-web, open-challenges, security-for-ai	raw
PAIEL: Protocol-Aware and Context-Integrated Protocol Explanation Using LLMs for SOCs	conference_paper	2026-02-23	ai-for-security, ai-soc, context-compression, protocol-analysis, rag, structured-context	raw
Non-Disruptive Disruption: An Empirical Experience of Introducing LLMs in the SOC	conference_paper	2026-02-23	ai-for-security, ai-soc, co-creation, ethnography, human-ai-collaboration	raw
Cognitive Threat Detection for SOC Operations: Automating Manipulation Tactic Analysis in Election S	conference_paper	2026-02-23	ai-for-security, ai-soc, cognitive-threat, election-security, llm-routing	raw
SuperLocalMemory: Privacy-Preserving Multi-Agent Memory with Bayesian Trust Defense Against Memory P	paper	2026-02-17	architectural-isolation, bayesian-trust, mas-misevolution-propagation, mcp, memory-poisoning, multi-agent-memory	raw
Memory Poisoning Propagation and Repair Mechanism in Multi-Agent Collaborative Environments	paper	2026-02-14	contrastive-learning, evidence-graph, mas-misevolution-propagation, memory-poisoning, multi-agent, propagation	raw
AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?	paper	2026-02-03	agent-security, benchmark, dynamic-tasks, prompt-injection, security-for-ai	raw
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks	paper	2026-02	agent-skills, benchmark, self-evolving-agents, self-generated-skills, skillsbench	raw
Security Threat Modeling for Emerging AI-Agent Protocols	paper	2026-02	agent-protocols, mcp-security, multi-agent, security-for-ai, threat-modeling	raw
DARPA's AI Cyber Challenge (AIxCC): Competition Design, Results, and Lessons	paper	2026-02	ai-for-security, aixcc, competition, cyber-reasoning-system, patching, vulnerability-discovery	raw
Memory Poisoning Attack and Defense on Memory Based LLM-Agents	paper	2026-01-09	memory-poisoning, memory-sanitization, query-only-attack, temporal-decay, trust-aware-retrieval	raw
Prompt Injection Attacks on Agentic Coding Assistants	paper	2026-01	agent-security, coding-agents, prompt-injection, security-for-ai, software-supply-chain	raw
Experiences of Using Agentic AI to Fill Tooling Gaps in a Security Operations Center	paper	2026	Faayed Al Faisal, Kritan Banstola, Xinming Ou, ai-agent, ai-for-security, alert-triage	raw
MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval	paper	2025-12-18	experience-retrieval, memory-poisoning, persistent-compromise, rollout-buffer-security	raw
AgentEvolver: Towards Efficient Self-Evolving Agent System	paper	2025-11-13	experience-pool, reinforcement-learning, rollout-buffer, self-evolving-agent, trajectory-attribution	raw
Whisper Leak: a side-channel attack on Large Language Models	paper	2025-11-05	Geoff McDonald, Jonathan Bar Or, llm-traffic-analysis, model-security, privacy, security-for-ai	raw
Securing AI Agent Execution	paper	2025-10-24	Christoph Bühler, Guido Salvaneschi, Luca Di Grazia, Matteo Biagiola, access-control, agent-security	raw
Carbon Filter: Scalable, Efficient, and Secure Alert Triage for Endpoint Detection & Response	conference_paper	2025-10-20	Adam Bates, Jonathan Oliver, Muhammad Adil Inam, Raghav Batta, ai-for-security, ai-soc	raw
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples	paper	2025-10	backdoors, data-poisoning, model-security, security-for-ai, training-data-security	raw
CORTEX: Collaborative LLM Agents for High-Stakes Alert Triage	paper	2025-09-30	Bowen Wei, Chris Jordan, Howard Liu, Jinhao Pan, Kun Luo, Yuan Shen Tay	raw
Large Language Models for Security Operations Centers: A Comprehensive Survey	paper	2025-09-13	Ali Habibzadeh, Farid Feyzi, Reza Ebrahimi Atani, ai-for-security, ai-soc, llm	raw
MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers	paper	2025-08-19	Guanquan Shi, Haifeng Sun, Haohua Du, Haoran Cheng, Suyuan Liu, Xiangyang Li	raw
Systematic Analysis of MCP Security	paper	2025-08-18	Peng Di, Puzhuo Liu, Sheng Wen, Wanlun Ma, Xi Xiao, Xiaogang Zhu	raw
Integrating Large Language Models into Security Incident Response	conference_paper	2025-08	Ajay Narotam, Allison Woodruff, Diana Kramer, Elie Bursztein, Kurt Thomas, Lambert Rosique	raw
A Survey on Model Extraction Attacks and Defenses for Large Language Models	paper	2025-06-26	Kaixiang Zhao, Kaize Ding, Lincan Li, Neil Zhenqiang Gong, Yue Zhao, Yushun Dong	raw
Design Patterns for Securing LLM Agents against Prompt Injections	paper	2025-06-10	agents, ai-security, defenses, design-patterns, prompt-injection	raw
CyberGym: Evaluating AI Agents' Cybersecurity Capabilities with Real-World Vulnerabilities at Scale	paper	2025-06-03	Dawn Song, Jialin Zhang, Jingxuan He, Matthew Cai, Tianneng Shi, Zhun Wang	raw
SEC-bench: Automated Benchmarking of LLM Agents on Real-World Security Tasks	paper	2025-06	ai-for-security, benchmark, llm-agents, security-tasks, vulnerability-reproduction	raw
LLMs in the SOC: An Empirical Study of Human-AI Collaboration in Security Operations Centres	paper	2025-06	Cecile Paris, Fatemeh Jalalvand, Martin Lochner, Mohan Baruwal Chhetri, Ronal Singh, Shahroz Tariq	raw
Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents	paper	2025-05-29	ai-technology, coding-agents, open-ended-evolution, recursive-self-improvement, self-improving-agents	raw
IRCopilot: Automated Incident Response with Large Language Models	paper	2025-05-27	Gelei Deng, Jie Zhang, Qing Guo, Riqing Chen, Tianwei Zhang, Tianzhe Liu	raw
Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control	paper	2025-05-23	access-control, auditability, collaborative-memory, mas-misevolution-propagation, multi-agent, provenance	raw
On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents	conference_paper	2025-05-01	autoinject, autotransform, challenger, faulty-agents, inspector, mas-misevolution-propagation	raw
Towards Secure Systems of Interacting AI Agents	paper	2025-05	agent-security, interaction-security, multi-agent, security-for-ai	raw
WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks	paper	2025-04-22	Aaron Grattafiori, Arman Zharmagambetov, Chuan Guo, Ivan Evtimov, Kamalika Chaudhuri, benchmark	raw
Alert Fatigue in Security Operations Centres: Research Challenges and Opportunities	journal_paper	2025-04-04	Cecile Paris, Mohan Baruwal Chhetri, Shahroz Tariq, Surya Nepal, ai-for-security, ai-soc	raw
Severity-based triage of cybersecurity incidents using kill chain attack graphs	journal_paper	2025-03	Basel Katt, Lukas Sadlek, Muhammad Mudassar Yamin, Pavel Celeda, ai-for-security, ai-soc	raw
CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities	paper	2025-03	ai-for-security, benchmark, cve-bench, exploit-evaluation, llm-agents, web-security	raw
AECR: Automatic attack technique intelligence extraction based on fine-tuned large language model	journal_paper	2025-03	Bin Lu, Ding Li, Kaijie Zhu, Minghao Chen, Qingjun Yuan, Yuefei Zhu	raw
GraphRAG under Fire	paper	2025-01	graphrag, poisoning, rag-security, retrieval, security-for-ai	raw
Transitioning from MLOps to LLMOps: Navigating the Unique Challenges of Large Language Models	paper	2025	ai-operations, ai-security, glossary-gap, large-language-model, llmops, mlops	raw
Model Retraining upon Concept Drift Detection in Network Traffic Data Streams	paper	2025	anomaly-detection, concept-drift, glossary-gap, mlops, model-drift, network-security	raw
EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit	paper	2025	data-exfiltration, enterprise-ai, incident-analysis, prompt-injection, security-for-ai	raw
CVE-Bench: Benchmarking LLM-based Software Engineering Agents' Ability to Fix Real-world Vulnerabili	paper	2025	ai-for-security, benchmark, cve-bench, software-engineering-agents, vulnerability-repair	raw
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges	paper	2025	agent-security, defenses, evaluation, security-for-ai, survey	raw
AI-Augmented SOC: A Survey of LLMs and Agents for Security Operations	paper	2025	ai-for-security, alert-triage, incident-response, llm-agents, security-operations, soc	raw
AgentOps: Enabling Observability of LLM Agents	paper	2024-11-08	Liming Dong, Liming Zhu, Qinghua Lu, agentops, ai-agent-observability, ai-safety	raw
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM Agents	paper	2024-10-03	agents, ai-security, benchmark, defenses, memory-poisoning, prompt-injection	raw
Large Language Models Can Provide Accurate and Interpretable Incident Triage	conference_paper	2024-10	Changhua Pei, Chaoyun Zhang, Chetan Bansal, Dongmei Zhang, Gaogang Xie, Jianhui Li	raw
Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models	paper	2024-08-15	ai-for-security, benchmark, capability-evaluation, ctf, cyber-range, llm-agents	raw
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery	paper	2024-08-12	ai-scientist, ai-technology, automated-scientific-discovery, open-ended-research, self-evolving-ai	raw
True Attacks, Attack Attempts, or Benign Triggers? An Empirical Measurement of Network Alerts in a S	conference_paper	2024-08	ai-for-security, ai-soc, alert-triage, empirical-measurement, ground-truth	raw
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models	paper	2024-08	backdoors, benchmark, llm-security, model-security, security-for-ai	raw
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases	paper	2024-07-17	agent-memory, backdoor, knowledge-base-poisoning, red-teaming, retrieval-trigger	raw
AI-Driven Guided Response for Security Operation Centers with Microsoft Copilot for Security	paper	2024-07-12	Amir Gharib, Jovan Kalajdjieski, Robert McCann, Scott Freitas, ai-for-security, ai-soc	raw
AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways	paper	2024-06-04	Changzhou Han, Junwu Xiong, Sheng Wen, Wanlun Ma, Yang Xiang, Yongjian Guo	raw
Security of AI Agents	paper	2024-06	agent-security, architecture, defenses, security-for-ai	raw
Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities	paper	2024-05-21	ai-for-security, datasets, genai, incident-response, survey, threat-detection	raw
Large Language Models for Cyber Security: A Systematic Literature Review	paper	2024-05-08	ai-for-security, llm4security, malware-analysis, survey, threat-intelligence, vulnerability-detection	raw
ExpeL: LLM Agents Are Experiential Learners	paper	2024-03-24	experience-pool, experiential-learning, faiss, retrieval, successful-trajectories	raw
InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents	paper	2024-03-05	agents, ai-security, benchmarks, prompt-injection, tool-use	raw
PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models	paper	2024-02-12	Binghui Wang, Jinyuan Jia, Runpeng Geng, Wei Zou, data-poisoning, knowledge-poisoning	raw
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training	paper	2024-01-10	Anthropic coauthors, Carson Denison, Evan Hubinger, Jesse Mu, Mike Lambert, backdoors	raw
CyberSecEval 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language M	paper	2024	ai-for-security, benchmark, cyberseceval, llm-evaluation, offensive-security, security-for-ai	raw
Benchmarking Prompt-Injection Attacks on Tool-Integrated LLM Agents	paper	2024	ai-security, data-exfiltration, privacy, prompt-injection, tool-integrated-agents	raw
Voyager: An Open-Ended Embodied Agent with Large Language Models	paper	2023-05-25	automatic-curriculum, embodied-agent, executable-code, lifelong-learning, skill-library	raw
Reflexion: Language Agents with Verbal Reinforcement Learning	paper	2023-03-20	episodic-memory-buffer, reflection, trajectory, verbal-reinforcement-learning	raw
Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Pro	paper	2023-02-23	Christoph Endres, Kai Greshake, Mario Fritz, Sahar Abdelnabi, Shailesh Mishra, Thorsten Holz	raw
That Escalated Quickly: An ML Framework for Alert Prioritization	preprint	2023-02-13	ai-for-security, ai-soc, alert-prioritization, machine-learning, managed-security	raw
Context2Vector: Accelerating security event triage via context representation learning	journal_paper	2022-06	ai-for-security, ai-soc, alert-triage, human-in-the-loop, representation-learning	raw
Improved Detection and Response via Optimized Alerts: Usability Study	journal_paper	2022-05-31	ai-for-security, ai-soc, alert-fatigue, machine-learning, usability	raw
DEEPCASE: Semi-Supervised Contextual Analysis of Security Events	conference_paper	2022-05	ai-for-security, ai-soc, deep-learning, event-correlation, semi-supervised-learning	raw
An Assessment of the Usability of Machine Learning Based Tools for the Security Operations Center	preprint	2020-12-16	ai-for-security, ai-soc, human-ai-collaboration, machine-learning, usability	raw
A user-centric machine learning framework for cyber security operations center	conference_paper	2017-07	ai-for-security, ai-soc, alert-triage, machine-learning, user-centric	raw
Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents	conference_paper		Shao, Shuai, agent-security, memory, misevolution, self-evolving-agents, tools	raw
SoK: The Attack Surface of Agentic AI -- Tools, and Autonomy	preprint		Dehghantanha, Ali, Homayoun, Sajad, agentic-ai, attack-surface, autonomy, multi-agent-security	raw
MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents	paper			raw
MAS Misevolution Propagation Collection 2026-06-26	collection_index	2026-06-26	collection, error-cascade, mas-misevolution-propagation, memory-poisoning, multi-agent, self-evolving-agents	raw
Explainable AI in Cybersecurity Operations: Lessons Learned from User Studies	paper	2026-06-16	analyst-decision-support, cybersecurity-operations, explainable-ai, glossary-gap, soc, xai	raw
Bounded Autonomy in the SOC: Mitigating Hallucinations in Agentic Incident Response via Neurosymboli	unknown			raw
BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents	paper			raw
AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber Operations	unknown			raw
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents	paper			raw
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents	paper			raw
AI Security Paper Collection 2026-06-29	collection	2026-06-29	ai-security, collection, papers, weekly-ingest	raw
AI SOC Q1 Journal and Peer-Reviewed Conference Collection	collection_manifest	2026-06-30	ai-for-security, ai-soc, collection-manifest, peer-reviewed, q1-journal	raw
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Sup	survey		Gao, agent-memory, agent-tools, self-evolving-agents, survey, taxonomy	raw