Sri Durga Sai Sowmya Kadali

University of California, Riverside

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Interpretability & Mechanistic Interp (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Evangelos E. Papalexakis (1)

Papers (1)

Feb 12, 2026

Feb 12, 2026·also UC Riverside

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models

LLMs betray their jailbreaking susceptibility in their hidden activations, allowing for lightweight detection and even real-time disruption of attacks.

Sri Durga Sai Sowmya Kadali, Evangelos E. Papalexakis

Interpretability & Mechanistic Interp Red-Teaming & Adversarial Robustness

Search

Sri Durga Sai Sowmya Kadali

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)