Latent-space Attacks for Refusal Evasion in Language Models

arXiv:2604.22117v1 Announce Type: cross Abstract: Aligned large language models(LLMs) remain vulnerable to adversarial manipulation, and their dependence on web-scale pretraining

<!-- SC_OFF --><div class="md"><p>I set out to test whether AAVE-coded (African American English Vernacular) prompts cause MoE language models to route, deliberate, and respond

arXiv:2606.13720v1 Announce Type: new Abstract: Arditi et al. (2024) has shown that refusal in safety fine-tuned chat models is mediated by a single linear direction in the

arXiv:2609.09553v1 Announce Type: cross Abstract: Large language model safety and security research is preoccupied with, among other things, detecting and preventing jailbreak

arXiv:2604.18663v1 Announce Type: cross Abstract: Existing jamming attacks on Retrieval-Augmented Generation (RAG) systems typically induce explicit refusals or denial-of-service

arXiv:2604.08557v1 Announce Type: cross Abstract: Diffusion-based language models (dLLMs) generate text by iteratively denoising masked token sequences. We show that their safety

arXiv:2604.22167v1 Announce Type: cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of

arXiv:2608.28233v1 Announce Type: new Abstract: Steering with Sparse Autoencoders (SAEs) offers a lightweight inference-time path for adapting the behavior of large language