Fine-tuning as Jailbreaking: A data-centric red teaming framework via logic injection

LogSanitizer: Defending LLM-Integrated SOCs against Backdoor Triggers Delivered through Firewall Logs

LogSanitizer is proposed, a family of input sanitization defenses operating at two levels: a pre-prompt log-transformation pipeline that disrupts trigger patterns in the structured log representation, and a post-tokenizer perturbation strategy that corrupts trigger-bearing token configurations before they reach the mod...

On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment

This work proposes Routing-based On-Policy Distillation (ROPD), a novel realignment framework that models the divergence between aligned and compromised output probability distributions rather than fitting specific prompt templates, establishing a new standard for robust LLM realignment.

RTLGuard: A Lightweight Teacher-Student Defense for Poisoned RTL Code Generation Models

RTLGuard leverages a teacher-student framework designed to sanitize compromised RTL generation models by fine-tuning a small-scale,"clean"teacher model on a limited set of trusted RTL data, and incorporating feature alignment and knowledge distillation to suppress malicious behaviors.

The 2nd SeT-LLM Workshop on Secure and Trustworthy Large Language Models

Large language models (LLMs) are increasingly embedded as core components of data-centric systems, supporting analytical decision making, and automated reasoning over large-scale, heterogeneous datasets. Yet their deployment in open-world environments raises fundamental challenges to security and trustworthiness: LLMs...

Jailbreaking Jailbreaks: A Proactive Defense for LLMs

Just Testing, Move Along: Evasion of LLM-based System Log Interpretation by Prompt Injection

This paper presents a framework for evaluating prompt injection attacks against LLM-based log interpretation using log traces generated during real cyber attacks, and creates adversarial examples through generic injection generation, refinement, and attack-specific optimization.