We have 6 of 12 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.
Multilingual safety evaluations should measure tool admission and response harmfulness separately and distinguish refusal from capability failure, as well as identify Safety Loss through Interlingual Processing (SLIP).
Large language models increasingly act as agents that call external tools, yet most tool-safety research examines only what follows a tool call. The prior decision of whether to call the tool remains largely unexamined and can influence downstream safety. Across the seven open-weight models, the unweighted model-averag...
DarKnight, a self-improving agentic framework designed to run on a single workstation GPU inside an investigator's Tor crawler and solve CAPTCHAs with small, locally hosted open-weight VLMs that no provider decision can withdraw, without per-market training or third-party services is presented.
Open-weight language models can be downloaded, modified, and deployed beyond their developers'control, limiting the effectiveness of centrally enforced safeguards. Recent work has therefore proposed \emph{trigger-tag} mechanisms that produce a detectable signal when a model is used under a target condition, such as gen...
Toketive is introduced, a simple yet powerful reference-free attack that exploits the tokenization-based side channel to detect modified knowledge and reconstruct the corresponding pre-edit response and shows that localized modifications should not be treated as robust knowledge-control boundaries without adversarial e...
This work introduces AgentREVEAL, a diagnostic framework for analyzing retrieval-induced safety degradation in LLM agents, and uncovers the Safe Source Paradox, a safety-utility trade-off for retrieval-enabled agents.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
