This study compares two methods of safety unalignment (Jailbreak-Tuning and Weight Orthogonalization) across six LLMs and finds that Weight Orthogonalization (WO) significantly enhances malicious capa…

The paper conducts an interpretability-driven safety audit of eight state-of-the-art LLMs, demonstrating that while interpretability-based steering is a powerful auditing tool, model robustness varies…

The paper evaluates multi-LLM strategies for secure code generation, finding that hybrid pipelines combining ensembling, static analysis, and patching achieve the strongest security performance, outpe…

This paper introduces Security Cube, a comprehensive, multi-dimensional framework for evaluating LLM robustness against jailbreak attacks, providing a systematic taxonomy and benchmark analysis of exi…

The paper proposes a novel pre-model safeguard that uses small draft models (SLMs) to predict the safety of prompts, significantly reducing false-negative rates while maintaining low computational ove…

The paper proposes EVA, a novel framework that uses direct model editing to surgically correct specific neurons responsible for jailbreaking vulnerabilities in LLMs and VLMs, achieving robust safety a…

This paper shifts the focus of LLM safety from preventing misalignment to investigating the model's intrinsic ability to self-recover its alignment after being corrupted by adversarial inputs.

The paper introduces an automated framework demonstrating that LLM system instructions are vulnerable to encoding attacks, where structured output requests can bypass safety refusals and leak sensitiv…

The paper investigates how various fine-tuning methods can be used both to intentionally misalign and subsequently realign large language models (LLMs), revealing distinct strengths for attack and def…

GuardNet is a lightweight, ensemble-based guardrail system using shallow neural networks that provides robust and efficient detection of Prompt Injection and Jailbreak attacks on LLMs, suitable for pr…

The paper introduces Babel, an efficient black-box attack framework that systematically exploits intrinsic safety gaps in LLMs by optimizing text obfuscation sampling, achieving state-of-the-art jailb…

The paper introduces TrojanMerge, a framework demonstrating that model merging can be exploited to systematically compromise the safety alignment of multiple individually safe LLMs.

The paper proposes Ablating Safety, a controlled protocol for removing safety alignment from language models, demonstrating that targeted de-alignment can significantly boost security performance whil…

The paper proposes GUARD-SLM, a token activation-based defense mechanism, to enhance the robustness of Small Language Models (SLMs) against various jailbreak attacks by analyzing and filtering malicio…

The paper introduces Distributed Semantic Recomposition (DSR), a novel cross-modal jailbreaking framework that bypasses existing safety filters by decomposing harmful intent into benign input componen…

SafeSteer proposes a localized on-policy distillation method that restricts safety alignment to specific safety tokens, thereby achieving strong safety performance with minimal degradation to general…

The paper proposes a novel zeroth-order optimization framework to enhance the robustness of LLM safety alignment, showing that few refinement steps can significantly improve safety while maintaining u…

The paper theorizes that aligned LLMs remain jailbreakable due to 'Refusal-Escape Directions' (RED), which are continuous perturbation paths that shift model behavior from refusal to answering, and sh…

The paper establishes a standardized security assessment framework and develops a multi-layered defensive system, demonstrating that systematic testing and external defenses are crucial for safe LLM d…