We have 7 of 18 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Large language models remain vulnerable to jailbreaks, and automated red teaming is the standard way to find jailbreaks in large language models at scale. Current methods either draw more samples at test time through search, rewriting, and tree expansion, or train a stronger attacker offline with reinforcement learning...
Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vulnerable to prompt injection attacks that can hijack task objectives. Existing safety alignment methods rely on static expert trajectories or preference optimization, lim...
AutoDojo is introduced, a generative benchmark built on AgentDojo and AgentDyn that generates IPI adaptively for a given agent and defense, and it is demonstrated that standard static benchmarks often significantly overestimate defense efficacy.
Internal representations thus support cross-mechanism attack-exposure auditing against calibrated benign references, but decouple from downstream task compromise and parameter integrity, according to downstream task compromise and parameter integrity.
It is argued that anomaly detection for agentic AI must reason at the workflow level, where global execution structure exposes signals that local checks cannot see, and presents Skynet, a principled workflow-level anomaly detection framework that turns observed multi-agent execution into directed workflow graphs and sc...
ROPE is presented, which is anchored in a structural notion of trust, and holds attack success rate to 1.6--2.6 while retaining 82--100% of undefended clean utility, significantly exceeding state-of-the-art system-level defenses in utility while attaining comparable or better security.
TokenPilot is presented, a dual-granularity context management framework that reduces costs by 61% and 56% in isolated mode, and 61% and 87% in continuous mode, while maintaining competitive performance compared to prior systems.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
