The paper introduces Semantic-level UI Element Injection, a novel red-teaming technique that overlays misleading UI elements onto screenshots to significantly improve the attack success rate against s…

This paper investigates a novel security vulnerability where imperceptible branding hints can be injected into images and subsequently re-rendered onto new objects by generative AI models, proposing b…

The paper introduces EditRisk-Bench, a novel benchmark designed to systematically evaluate the safety risks and downstream reasoning corruption caused by malicious knowledge editing in large language…

This paper introduces TwoHamsters, a new benchmark that rigorously tests Multi-Concept Compositional Unsafety (MCCU) in text-to-image models, demonstrating that current state-of-the-art models and saf…

The paper proposes a general-purpose pipeline to train automated red teaming models capable of generating attacks for arbitrary adversarial goals, overcoming the limitations of current methods that ar…

The paper benchmarks current frontier computer-using agents against hand-crafted attacks, finding that while they are highly safe in browser tasks, this safety does not generalize to other domains lik…

The paper introduces OS-BLIND, a benchmark demonstrating that current safety evaluations fail to detect critical vulnerabilities in computer-use agents when user instructions are benign, showing high…

The paper introduces SkillSafetyBench, a comprehensive benchmark demonstrating that agent safety failures often stem from adversarial influences within reusable skills and execution environments, rath…

The paper introduces ClawTrap, a MITM-based red-teaming framework, to evaluate the security robustness of web agents like OpenClaw against dynamic, real-world network attacks, finding that model stren…

The paper introduces IPI-proxy, an open-source intercepting proxy toolkit designed to red-team web-browsing AI agents by injecting adversarial payloads into live HTTP responses from whitelisted domain…

The paper introduces SafeRedirect, a system-level defense that prevents frontier LLMs from generating harmful content during legitimate tasks that structurally require it, significantly reducing unsaf…

ARES is a novel framework that systematically discovers and mitigates dual vulnerabilities in RLHF systems by simultaneously testing the core LLM and its Reward Model (RM) using structured adversarial…

The paper introduces an AI red teaming agent that drastically reduces the time and effort required for security testing by allowing operators to define complex attack goals using natural language, com…

The paper demonstrates that adversarial examples can be used to manipulate Vision-Language Models (VLMs) into confidently providing authoritative but incorrect information, a process termed 'AI author…

AutoRISE proposes optimizing the entire attack strategy—by searching over executable programs—rather than just optimizing prompts, achieving significant improvements in red-teaming large language mode…

OrchJail introduces an orchestration-guided fuzzing framework to systematically jailbreak tool-calling text-to-image agents by exploiting unsafe multi-step tool-orchestration patterns.

The paper introduces REFORGE, a black-box red-teaming framework that uses adversarial image prompts to reveal persistent vulnerabilities in current Image Generation Model Unlearning (IGMU) methods.

The paper conducts a preliminary safety evaluation of the open-weight LLM Kimi K2.5, finding that while it is highly capable, it exhibits concerning dual-use risks, particularly regarding CBRNE misuse…

The paper introduces AGENTREDBENCH, a dynamic redteaming benchmark that significantly measures indirect prompt injection threats in LLM agents using third-party integrations, and releases AGENTREDGUAR…

The paper introduces AGENTREDBENCH, a dynamic redteaming benchmark that significantly measures indirect prompt injection threats in LLM agents using SaaS integrations, and releases AGENTREDGUARD, a su…