Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits

• URL: http://arxiv.org/abs/2608.07430v1
• Date: Fri, 07 Aug 2026 17:17:18 GMT
• Title: Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits
• Abstract summary: We show that safety alignment inDLLMs remains sparse and transferable across architectures.<n>We introduce SN-Guided Diffusion, a fully offline black-box jailbreak framework.<n>Our method achieves competitive transferability with orders-of-magnitude lower generation cost.
• Score: 5.982945107343805
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mechanisms remain poorly understood. In this work, we investigate DLLMs both as targets and as adversaries, exposing mechanistic vulnerabilities in diffusion-based alignment. We first show that safety alignment in DLLMs remains sparse and transferable across architectures. DLLMs initialized from autoregressive predecessors inherit the same mechanistic safety footprint as their source models, enabling transfer attacks via direct safety neuron mapping and pruning. Self-pruning increases attack success rates (ASR) from 2.6% to 73.8% on LLaDA and from 1.9% to 86.6% on Dream, while transfer pruning from Qwen2.5 increases ASR from 1.9% to 73.2% on Dream and from 7.0% to 86.3% on Fast-dLLM. Building on these findings, we introduce SN-Guided Diffusion, a fully offline black-box jailbreak framework that steers the diffusion process away from safety-triggering regions using a weighted safety neuron loss, which achieves near-perfect prompt separability (AUROC = 1.0 for benign-vs-jailbreak discrimination). Across multiple open and proprietary targets, our method achieves a transfer ASR of up to 77.1% on Llama-3-8B-Instruct, 86.9% on Qwen2.5-7B-Instruct, and 74.3% against Gemini-2.5-Flash-Lite, while requiring only 20 generation episodes per prompt. Compared to prior jailbreaking frameworks, our method achieves competitive transferability with orders-of-magnitude lower generation cost. Our codebase is available at https://github.com/ellyoana/sn-guided-diffusion.

Related papers

• Modality-Decoupled Federated Learning for Privacy-Preserving Embodied Intelligence in 6G [90.42669277637026]
  Sixth-generation (6G) wireless networks are expected to provide a key infrastructure for large-scale embodied intelligence.<n>This article proposes FedMVLA, a modality-decoupled FL framework for privacy-preserving embodied intelligence in 6G networks.
  arXiv  Detail & Related papers  (2026-09-09T01:36:44Z)
• The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs [1.4323566945483497]
  We introduce Contrastive Logit Steering ( CLS), a zero-optimization framework that isolates the "refusal direction"<n> CLS operates directly on the output distribution, serving as a diagnostic probe for alignment.<n>Our experiments on 7 model families reveal that safety implementation is architecturally deterministic.
  arXiv  Detail & Related papers  (2026-06-21T22:04:48Z)
• Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language Models [0.0]
  Safety alignment in diffusion language models (dLLMs) relies on a single load-bearing assumption: committed tokens are permanent.<n>We show that by re-masking committed refusal tokens and injecting a short affirmative prefix, achieves 74-82% ASR on HarmBench.<n>We call this attack TrajHijack; it is the first trajectory-level attack on dLLMs, requires no computation, and generalizes across SFT and preference-optimized (VRPO) models.
  arXiv  Detail & Related papers  (2026-03-17T02:24:37Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• A Fragile Guardrail: Diffusion LLM's Safety Blessing and Its Failure Mode [51.43498132808724]
  We show that Diffusion large language models (D-LLMs) have intrinsic robustness against jailbreak attacks.<n>We identify a simple yet effective failure mode, termed context nesting, where harmful requests are embedded within structured benign contexts.<n>We show that this simple strategy is sufficient to bypass D-LLMs' safety blessing, achieving state-of-the-art attack success rates.
  arXiv  Detail & Related papers  (2026-01-30T23:08:14Z)
• GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs [24.327693899810615]
  We present GateBreaker, the first training-free, lightweight, and architecture-agnostic attack framework.<n>GateBreaker compromises the safety alignment of modern MoE LLMs at inference time.<n>Our study shows that MoE safety concentrates within a small subset of neurons coordinated by sparse routing.
  arXiv  Detail & Related papers  (2025-12-24T07:13:24Z)
• DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models [50.21378052667732]
  We conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics.<n>We propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach.
  arXiv  Detail & Related papers  (2025-09-29T05:17:10Z)
• Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities [50.980446687774645]
  We introduce ADV-LLM, an iterative self-tuning process that crafts adversarial LLMs with enhanced jailbreak ability.<n>Our framework significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100% ASR on various open-source LLMs.<n>It exhibits strong attack transferability to closed-source models, achieving 99% ASR on GPT-3.5 and 49% ASR on GPT-4, despite being optimized solely on Llama3.
  arXiv  Detail & Related papers  (2024-10-24T06:36:12Z)
• Improved Generation of Adversarial Examples Against Safety-aligned LLMs [72.38072942860309]
  Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. In this paper, we explore a new perspective on this problem, suggesting that it can be alleviated by leveraging innovations inspired in transfer-based attacks. We show that 87% of the query-specific adversarial suffixes generated by the developed combination can induce Llama-2-7B-Chat to produce the output that exactly matches the target string on AdvBench.
  arXiv  Detail & Related papers  (2024-05-28T06:10:12Z)
• Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization [98.18718484152595]
  We propose to integrate goal prioritization at both training and inference stages to counteract the intrinsic conflict between the goals of being helpful and ensuring safety. Our work thus contributes to the comprehension of jailbreaking attacks and defenses, and sheds light on the relationship between LLMs' capability and safety.
  arXiv  Detail & Related papers  (2023-11-15T16:42:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.