We have 4 of 70 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.
GuidedBench, a novel benchmark comprising a curated harmful question dataset and GuidedEval, an evaluation system integrated with detailed case-by-case evaluation guidelines are introduced, ensuring reliable and reproducible evaluations.
This work proposes ReDiR, a generation-time defense that conditions action generation on trajectory-level security evidence and reduces attack success rates to below 8%, transfers to unseen tool domains, and preserves benign fidelity with low computational overhead.
These findings reveal substantial hidden dependencies among seemingly independent API resellers, which can create a large potential blast radius, where a confidentiality or integrity failure along a common upstream path may affect users across multiple downstream resellers.
This initial study demonstrates that directly prompting off-the-shelf code LLMs remains ineffective; even advanced prompting strategies cannot compensate for the lack of task-specific knowledge, and fine-tuning proves highly effective, with pseudo-code representation consistently yielding the best performance.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
