AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 4 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.
ReCode is introduced, a compositional budget-efficient attack that combines desensitization rewriting with two effective low-cost primitives identified by Fair-ASR, to provide a comparable evaluation basis for black-box jailbreak attacks under shared target-call budgets B.
The routed-state interface unifies contextual memory and persistent capability adaptation within the model's native computation, reframing memory from a passive record of prior context into an active substrate for maintaining and evolving model behavior.
This work introduces \textsc{JailbreakSkill}, a skill-centric framework for scaling automated red-teaming through reusable and continuously evolving attack capabilities, which packages existing attack strategies into modular, agent-ready skills that can be directly reused and adaptively selected across tasks and target models.
This work presents SkillSafetyBench, a runnable benchmark for evaluating skill-facing safety failures, and suggests that agent safety depends not only on model-level alignment, but also on how agents interpret skills, trust workflow context, and act through executable environments.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.