Autonomous OSS Threat Detection via Taxonomy-Aligned LLMs

from sophisticated supply chain attacks including typosquatting, dependency confusion, Trojan Source obfuscation, malicious build injection, and CI/CD pipeline poisoning. Existing detection approaches rely on signature-based tools and rule-based

OI-Bench: An Option Injection Benchmark for Evaluating LLM Susceptibility to Directive Interference

signals such as social cues, framing, and instructions. In this work, we introduce option injection, a benchmarking approach that augments the multiple-choice question answering (MCQA) interface with an additional

Mistune Image Directive CSS Injection Vulnerability

The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills

distance. Our central claim is that keeping the fingerprint as a per-component triple (prompt, code, tools), rather than a single score, is what makes it useful: the triple recovers

Routing Ceilings Are Domain-Independent: Structural Prior Injection in Code Security Vulnerability Detection

Large language models (LLMs) exhibit a well-documented gap between

How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency

Large language models (LLMs) can autonomously conduct multi-stage cyber

Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models

workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn Injection(TTI), a new multi-turn attack technique that systematically exploits stateless moderation by distributing adversarial

Cross-Session Threats in AI Agents: Benchmark, Evaluation, and Algorithms

attack taxonomies classified by kill-chain stage and cross-session operation (accumulate, compose, launder, inject_on_reader), each bound to one of seven identity anchors that ground-truth "violation

Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse

Traditional backdoor attacks inject artificial trigger patterns into training data, causing models to misclassify triggered inputs while maintaining normal behavior on clean samples. Since these artificial triggers are absent

TriFleetRCA: On-Premise LLM Root Cause Analysis for Kubernetes

evidence lines supporting it. We evaluate on a live Kubernetes cluster into which we inject four faults, so ground truth is known by construction, across 100 analyses with Qwen2.5-14B-Instruct

ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers

Large language models are being integrated into malware triage workflows

MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration

multi-objective problem: functional correctness and security. Existing approaches address this challenge by injecting external security knowledge or by using agentic feedback and iterative refinement. However, guideline retrieval often leaves

Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents

Agentic red-teaming benchmarks report whether an injected agent was

The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure

domain-specific narratives and propagated to a Manager through Worker reports, without any syntactic injection primitives. Across 42,000 adversarial trials over 12 Manager models and 7 Worker configurations

Whisper Leak: a side-channel attack on Large Language Models

paramount. This paper introduces Whisper Leak, a side-channel attack that infers user prompt topics from encrypted LLM traffic by analyzing packet size and timing patterns in streaming responses. Despite

Has the Two-Decade-Old Prophecy Come True? Artificial Bad Intelligence Triggered by Merely a Single-Bit Flip in Large Language Models

Recently, Bit-Flip Attack (BFA) has garnered widespread attention for