We have 5 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.
Activation steering manipulates large language model behavior by intervening on internal activations, but the mechanistic basis of these interventions remains poorly understood. We decompose refusal steering into component-level interventions across four open-weight models, identifying the sparse subsets of attention a...
This work operationalizes contextual security through four properties that must hold jointly and be evaluated continuously across the agent's trajectory, which changes which defenses are coherent, which evaluations measure something useful, and which attack patterns evaluation can see at all.
Whether an instruction-tuned model calls a tool can be controlled by a single linear direction in its residual stream, extracted without any training from the model's own tool-use preference signal and turned into an inference-time intervention with no prompt change.
SafeClawArena is developed, a benchmark of 406 adversarial tasks executed in containerized replicas of real agent platforms with canary-marked credentials and evaluated via automated taint tracking across nine output channels, exposing the inadequacy of current defenses and suggesting directions for future hardening.
ChainWorld, which composes atomic OSWorld tasks into long horizon desktop workloads through directional compatibility search while preserving the source evaluators, is studied, which contains 347 chains of length two to four and compares two renderings of the same task sequence.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
