PRISM is a new activation-conditioned model that recovers full sets of simultaneous instructions from LLM hidden states via judge-guided GRPO training and outperforms prior activation-to-language methods on security-relevant tasks.
A da S teer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender
4 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Low-resource safety failures are action failures because the harmfulness representation transfers but the decision calibration does not; this is fixed by recalibrating a high-resource gate with 1-4 target-language examples.
Activation steering is cast as constrained optimization that minimizes collateral damage by weighting perturbations according to the empirical second-moment matrix of activations instead of assuming isotropy.
TrajGuard detects jailbreaks by tracking how hidden-state trajectories move toward high-risk regions during decoding, achieving 95% defense rate with 5.2 ms/token latency across tested attacks.
citing papers explorer
-
PRISM: Recovering Instruction Sets from Language Model Activations
PRISM is a new activation-conditioned model that recovers full sets of simultaneous instructions from LLM hidden states via judge-guided GRPO training and outperforms prior activation-to-language methods on security-relevant tasks.
-
Low-Resource Safety Failures Are Action Failures, Not Representation Failures
Low-resource safety failures are action failures because the harmfulness representation transfers but the decision calibration does not; this is fixed by recalibrating a high-resource gate with 1-4 target-language examples.
-
Minimizing Collateral Damage in Activation Steering
Activation steering is cast as constrained optimization that minimizes collateral damage by weighting perturbations according to the empirical second-moment matrix of activations instead of assuming isotropy.
-
TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense
TrajGuard detects jailbreaks by tracking how hidden-state trajectories move toward high-risk regions during decoding, achieving 95% defense rate with 5.2 ms/token latency across tested attacks.