A clustering-based stateful online monitor detects distributed multi-agent cyberattacks that evade standard per-transcript monitors, catching them 30% earlier in large-scale simulated traffic with low overhead.
Zhang, Joey Ji, Celeste Menders, Riya Dulepet, T
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 8roles
background 3representative citing papers
LLM agents exhibit persistent attack-selection biases as fixed traits independent of success rates, with a bias momentum effect that resists steering and yields no performance gain.
AuditBench is a new benchmark of audit logs from 50+ malicious and benign scenarios that evaluates five LLMs on four security investigation tasks and analyzes their performance and error profiles.
An evaluation protocol for AI pentesting agents that scores validated vulnerability discovery using LLM-based semantic matching and bipartite resolution.
Empirical comparison of agentic topologies for offensive security shows MAS-Indep reaching 64.2% validated detection while simpler baselines remain competitive on efficiency, with whitebox and web targets outperforming blackbox and binary ones.
Claude 4.5 Opus reaches 59% solve rate on offensive cyber CTF tasks, with a Kali Linux environment adding 9.5 percentage points over Ubuntu while prompt engineering often hurts performance in equipped setups.
AlphaEval is a benchmark of 94 production-sourced tasks from seven companies for evaluating full AI agent products across six domains using multiple judgment methods, plus a framework to build similar benchmarks.
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
citing papers explorer
-
Stateful Online Monitoring Catches Distributed Agent Attacks
A clustering-based stateful online monitor detects distributed multi-agent cyberattacks that evade standard per-transcript monitors, catching them 30% earlier in large-scale simulated traffic with low overhead.
-
CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
LLM agents exhibit persistent attack-selection biases as fixed traits independent of success rates, with a bias momentum effect that resists steering and yields no performance gain.
-
Benchmarking and Exploring the Capabilities of LLMs for Attack Investigations
AuditBench is a new benchmark of audit logs from 50+ malicious and benign scenarios that evaluates five LLMs on four security investigation tasks and analyzes their performance and error profiles.
-
From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World
An evaluation protocol for AI pentesting agents that scores validated vulnerability discovery using LLM-based semantic matching and bipartite resolution.
-
Towards Optimal Agentic Architectures for Offensive Security Tasks
Empirical comparison of agentic topologies for offensive security shows MAS-Indep reaching 64.2% validated detection while simpler baselines remain competitive on efficiency, with whitebox and web targets outperforming blackbox and binary ones.
-
Systematic Capability Benchmarking of Frontier Large Language Models for Offensive Cyber Tasks
Claude 4.5 Opus reaches 59% solve rate on offensive cyber CTF tasks, with a Kali Linux environment adding 9.5 percentage points over Ubuntu while prompt engineering often hurts performance in equipped setups.
-
AlphaEval: Evaluating Agents in Production
AlphaEval is a benchmark of 94 production-sourced tasks from seven companies for evaluating full AI agent products across six domains using multiple judgment methods, plus a framework to build similar benchmarks.
-
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.