arXiv AI
Jun 19
SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling
arXiv:2606. 19755v1 Announce Type: cross Abstract: Speculative inference accelerates large language model (LLM) decoding but provides no inherent safety guarantees.
Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models
Related stories
arXiv AI
Sep 28
Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis
The paper proposes a framework that explains why jailbreak attacks succeed against diffusion-based large language models (dLLMs) by viewing safety alignment as shaping a denoising energy landscape. It identifies two attack strategies—obscuring the query’s safety disposition at initialization or forcing the denoising path across an energy barrier mid‑trajectory—and introduces three training‑free detection signals that monitor initial safety disposition and kinetic energy in complementary subspaces. Experiments on several dense and sparse dLLMs show that these signals complement each other, and any attack that evades detection also fails to produce harmful content.
arXiv AI
Jun 4
Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories
arXiv:2606. 04778v1 Announce Type: new Abstract: Safety-aligned Large Language Models (LLMs) remain vulnerable to interventions during inference that redirect generation toward harmful outputs.
Hugging Face Trending Papers
Jul 2
Safety Targeted Embedding Exploit via Refinement
Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training.
arXiv AI
Jun 4
MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models
arXiv:2606. 04027v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autoregressive LLMs.
arXiv Machine Learning
Jun 3
Backdooring Masked Diffusion Language Models
arXiv:2605. 19262v2 Announce Type: replace Abstract: Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored.
arXiv AI
Jul 3
Safety Targeted Embedding Exploit via Refinement
arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.
arXiv Machine Learning
6d ago
Refusal Is Not Robustness: Measuring Harmful Reachability in Autoregressive Language Models
The paper introduces Bounded Continuation Analysis (BCA), a method that models autoregressive language model generation as a stochastic process over token prefixes to compute the finite‑horizon probability of reaching a harmful continuation. BCA builds a bounded continuation tree, labels terminal continuations with a semantic harm evaluator, and uses exact probabilistic model checking to estimate harmful reachability. Unlike traditional attack success rate (ASR) metrics that only assess sampled outputs, BCA reveals hidden harmful paths that may coexist with safe responses, enabling more precise red‑team targeting across instruction‑tuned LLMs and JailbreakBench behaviors.
arXiv AI
Sep 30
Controlled Decoding Attacks on Black-Box LLMs
arXiv:2609.36956v1 Announce Type: cross Abstract: Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely...
arXiv Machine Learning
2d ago
Harmful Responses Are Jailbreak Templates: Transferring Autoregressive Jailbreaks to Diffusion Language Models
The paper introduces RMT-Jailbreak, a method that transfers autoregressive jailbreak attacks to diffusion large language models (dLLMs). By masking tokens in a harmful response generated by an autoregressive model, the approach creates a high‑mask‑ratio template that, when fed to a dLLM, prompts it to reconstruct the harmful content. Experiments show that this technique effectively transfers jailbreak attacks across different models, highlighting a new vulnerability in diffusion-based language models.
Hugging Face Trending Papers
Jun 4
Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack
Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.
arXiv Machine Learning
Jul 14
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
arXiv:2607. 09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility.