3 papers
cs.CR2026
Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
Sri Durga Sai Sowmya Kadali, Evangelos E. Papalexakis
Jailbreaking large language models (LLMs) has emerged as a critical security challenge with the widespread deployment of conversational AI systems. Adversarial users exploit these…
cs.CL2025
Do Internal Layers of LLMs Reveal Patterns for Jailbreak Detection?
Sri Durga Sai Sowmya Kadali, Evangelos E. Papalexakis
Jailbreaking large language models (LLMs) has emerged as a pressing concern with the increasing prevalence and accessibility of conversational LLMs. Adversarial users often exploit…
cs.CL2025
CoCoTen: Detecting Adversarial Inputs to Large Language Models through Latent Space Features of Contextual Co-occurrence Tensors
Sri Durga Sai Sowmya Kadali, Evangelos E. Papalexakis
The widespread use of Large Language Models (LLMs) in many applications marks a significant advance in research and practice. However, their complexity and hard-to-understand natur…