English
Related papers

Related papers: Re-Mask and Redirect: Exploiting Denoising Irrever…

200 papers

RLHF-style alignment trains language models to refuse unsafe requests, but how much operational margin does this refusal rest on? We introduce the refusal-affirmation logit gap: the difference between the top refusal-token logit and the top…

Cryptography and Security · Computer Science 2026-05-05 Tung-Ling Li , Hongliang Liu

Diffusion-based decoding has recently emerged as an appealing alternative to autoregressive (AR) generation, offering the potential to update multiple tokens in parallel and reduce latency. However, diffusion vision language models (dVLMs)…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Lunbin Zeng , Jingfeng Yao , Bencheng Liao , Hongyuan Tao , Wenyu Liu , Xinggang Wang

Unified architectures in multimodal large language models (MLLM) have shown promise in handling diverse tasks within a single framework. In the text-to-speech (TTS) task, current MLLM-based approaches rely on discrete token representations,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-27 Xinlu He , Swayambhu Nath Ray , Harish Mallidi , Jia-Hong Huang , Ashwin Bellur , Chander Chandak , M. Maruf , Venkatesh Ravichandran

Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary…

Cryptography and Security · Computer Science 2026-05-14 Zvi Topol

Diffusion Language Models (DLMs) offer a promising alternative for language modeling by enabling parallel decoding through iterative refinement. However, most DLMs rely on hard binary masking and discrete token assignments, which hinder the…

Computation and Language · Computer Science 2026-01-19 Linhao Zhong , Linyu Wu , Bozhen Fang , Tianjian Feng , Chenchen Jing , Wen Wang , Jiaheng Zhang , Hao Chen , Chunhua Shen

To generate data from trained diffusion models, most inference algorithms, such as DDPM, DDIM, and other variants, rely on discretizing the reverse SDEs or their equivalent ODEs. In this paper, we view such approaches as decomposing the…

Machine Learning · Statistics 2024-05-28 Xunpeng Huang , Difan Zou , Hanze Dong , Yi Zhang , Yi-An Ma , Tong Zhang

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Machine Learning · Computer Science 2025-08-22 Xiangman Li , Xiaodong Wu , Qi Li , Jianbing Ni , Rongxing Lu

Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignment, safety, preference satisfaction, and robustness to misuse. This survey reviews recent…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Preeti Lamba , Kiran Ravish , Ankita Kushwaha , Pawan Kumar

Adversarial training for LLMs is one of the most promising methods to reliably improve robustness against adversaries. However, despite significant progress, models remain vulnerable to simple in-distribution exploits, such as rewriting…

Machine Learning · Computer Science 2026-02-19 Chengzhi Hu , Jonas Dornbusch , David Lüdke , Stephan Günnemann , Leo Schwinn

In the realm of black-box jailbreak attacks on large language models (LLMs), the feasibility of constructing a narrow safety proxy, a lightweight model designed to predict the attack success rate (ASR) of adversarial prompts, remains…

Cryptography and Security · Computer Science 2025-12-01 Tianyu Zhang , Zihang Xi , Jingyu Hua , Sheng Zhong

As large language models (LLMs) become increasingly prevalent and integrated into autonomous systems, ensuring their safety is imperative. Despite significant strides toward safety alignment, recent work GCG~\citep{zou2023universal}…

Computation and Language · Computer Science 2024-11-26 Zeyi Liao , Huan Sun

Autoregressive language models are widely used for text evaluation, however, their left-to-right factorization introduces positional bias, i.e., early tokens are scored with only leftward context, conflating architectural asymmetry with…

Computation and Language · Computer Science 2026-05-13 Wen Lai , Yingli Shen , Dingnan Jin , Qing Cui , Jun Zhou , Maosong Sun , Alexander Fraser

Diffusion language models (dLMs) have emerged as a promising paradigm that enables parallel, non-autoregressive generation, but their learning efficiency lags behind that of autoregressive (AR) language models when trained from scratch. To…

Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…

Sound · Computer Science 2026-01-27 Wenjie Tian , Bingshen Mu , Guobin Ma , Xuelong Geng , Zhixian Zhao , Lei Xie

Large Language Models (LLMs) demonstrate complex responses to threat-based manipulations, revealing both vulnerabilities and unexpected performance enhancement opportunities. This study presents a comprehensive analysis of 3,390…

Cryptography and Security · Computer Science 2025-07-30 Atil Samancioglu

In recent years, large language models (LLMs) have demonstrated notable success across various tasks, but the trustworthiness of LLMs is still an open problem. One specific threat is the potential to generate toxic or harmful responses.…

Cryptography and Security · Computer Science 2024-06-11 Tong Liu , Yingjie Zhang , Zhe Zhao , Yinpeng Dong , Guozhu Meng , Kai Chen

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…

Computation and Language · Computer Science 2026-02-03 Zehua Cheng , Jianwei Yang , Wei Dai , Jiahao Sun

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models for language modeling, allowing flexible generation order and parallel generation of multiple tokens. However, this flexibility…

Machine Learning · Computer Science 2026-03-24 Changxiao Cai , Gen Li

Diffusion language models are a promising alternative to autoregressive models due to their potential for faster generation. Among discrete diffusion approaches, Masked diffusion currently dominates, largely driven by strong perplexity on…

Machine Learning · Computer Science 2026-02-17 Subham Sekhar Sahoo , Jean-Marie Lemercier , Zhihan Yang , Justin Deschenaux , Jingyu Liu , John Thickstun , Ante Jukic

Diffusion-based large language models (DLLMs) have shown promise for non-autoregressive text generation, but their deployment is constrained by large model sizes and heavy computational costs. Post-training quantization (PTQ), a widely used…

Computation and Language · Computer Science 2025-08-27 Chen Xu , Dawei Yang