This paper introduces AgentREVEAL, a diagnostic framework showing that the utility of web retrieval in LLM agents creates a safety-utility trade-off, as relevance itself can degrade safety alignment a…

This paper addresses the critical need for trustworthy LLMs in science by proposing a comprehensive, multi-layered defense framework and methodology to evaluate unique scientific vulnerabilities.

This paper introduces HarmAmp, a new benchmark for multi-turn harm amplification, and proposes TrajSafe, a proactive monitoring system that significantly reduces harmfulness in LLM interactions while…

The paper analyzes how runtime safety enforcement impacts the performance of multi-step LLM agents, finding that while safety mechanisms can block unsafe actions, they impose a significant performance…

The paper proposes a layered, server-side isolation architecture to secure Retrieval-Augmented Generation (RAG) and agentic AI systems in multitenant enterprise environments, ensuring that retrieval a…

The paper introduces Entity-Collision, a rigorous protocol that separates genuine retrieval lift from simple lexical overlap, demonstrating that embedder performance depends critically on the query ty…

The paper demonstrates a semantic denial-of-service attack against LLM-controlled robots by injecting short, safety-plausible phrases into the audio channel, causing the robot to halt or disrupt execu…

The paper demonstrates that deep-research agents are vulnerable to poisoning attacks where an adversary can inject malicious content into a single, frequently retrieved user-generated page to compromi…

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 analyzes the escalating security and safety threats posed by generative AI systems as they transition from merely generating content to executing real-world actions via tools and agents, fin…

SPARD is a defense framework that uses Safety-Projected Alternating optimization and Relevance-Diversity data selection to protect large language models from harmful fine-tuning attacks, achieving sup…

SPARD is a defense framework that uses Safety-Projected Alternating optimization and Relevance-Diversity data selection to mitigate harmful fine-tuning attacks that undermine LLM safety.

The study evaluates how safety alignment affects autonomous security agents using a comprehensive trace-based benchmark, finding that while less-restricted models show gains, these effects are not uni…

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 SafeHarness, a novel, lifecycle-integrated security architecture that significantly reduces unsafe behavior and attack success rates in LLM agents by weaving multiple defense laye…

The paper introduces an automated framework demonstrating that LLM system instructions are vulnerable to encoding attacks, where structured output requests can bypass safety refusals and leak sensitiv…

The paper introduces BOA, a novel framework that measures agent safety by exhaustively searching the entire in-budget trajectory space, thereby identifying unsafe behaviors missed by traditional sampl…

The paper introduces RUBAS, a rubric-based reinforcement learning framework that improves agent safety by providing fine-grained, multi-dimensional rewards for complex tool-use scenarios.

The paper introduces RAVEN, a Retrieval-Augmented Vulnerability Exploration Network, which uses LLM agents and RAG to automatically generate comprehensive, structured vulnerability analysis reports fo…