English
Related papers

Related papers: A2D: Any-Order, Any-Step Safety Alignment for Diff…

200 papers

Large language models (LLMs) remain vulnerable to jailbreak prompts that elicit harmful or policy-violating outputs, while many existing defenses rely on expensive fine-tuning, intrusive prompt rewriting, or external guardrails that add…

Cryptography and Security · Computer Science 2026-02-17 Weiming Song , Xuan Xie , Ruiping Yin

Diffusion large language models (dLLMs) gain speed by committing multiple tokens in parallel at each denoising step, but any erroneous commitment persists as conditioning context and biases every subsequent prediction. LLaDA2.1 repairs such…

Computation and Language · Computer Science 2026-05-08 Lin Yao

Large language models have achieved remarkable success under the autoregressive paradigm, yet high-quality text generation need not be tied to a fixed left-to-right order. Existing alternatives still struggle to jointly achieve generation…

Computation and Language · Computer Science 2026-05-08 Hongcan Guo , Qinyu Zhao , Yian Zhao , Shen Nie , Rui Zhu , Qiushan Guo , Feng Wang , Tao Yang , Hengshuang Zhao , Guoqiang Wei , Yan Zeng

In the rapidly evolving field of machine learning, adversarial attacks present a significant challenge to model robustness and security. Decision-based attacks, which only require feedback on the decision of a model rather than detailed…

Cryptography and Security · Computer Science 2024-05-24 Ping Guo , Fei Liu , Xi Lin , Qingchuan Zhao , Qingfu Zhang

Large language models (LLMs) are increasingly deployed worldwide, yet their safety alignment remains predominantly English-centric. This allows for vulnerabilities in non-English contexts, especially with low-resource languages. We…

Computation and Language · Computer Science 2026-04-27 Max Zhang , Derek Liu , Kai Zhang , Joshua Franco , Haihao Liu

Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as any target labels.…

Machine Learning · Computer Science 2018-04-11 Pu Zhao , Sijia Liu , Yanzhi Wang , Xue Lin

Large language models (LLMs), despite possessing latent safety understanding from their vast pretraining data, remain vulnerable to generating harmful content and exhibit issues such as over-refusal and utility degradation after safety…

Artificial Intelligence · Computer Science 2025-07-22 Yi Zhang , An Zhang , XiuYu Zhang , Leheng Sheng , Yuxin Chen , Zhenkai Liang , Xiang Wang

Alignment in large language models (LLMs) is used to enforce guidelines such as safety. Yet, alignment fails in the face of jailbreak attacks that modify inputs to induce unsafe outputs. In this paper, we introduce and evaluate a new…

Cryptography and Security · Computer Science 2026-02-19 Jean-Charles Noirot Ferrand , Yohan Beugin , Eric Pauley , Ryan Sheatsley , Patrick McDaniel

Diffusion-based large language models (dLLMs) are gaining attention for their inherent capacity for parallel decoding, offering a compelling alternative to autoregressive LLMs. Among various decoding strategies, block-wise…

Machine Learning · Computer Science 2026-03-03 Guanxi Lu , Hao Mark Chen , Yuto Karashima , Zhican Wang , Daichi Fujiki , Hongxiang Fan

As Large Language Models (LLMs) are increasingly being deployed in safety-critical applications, their vulnerability to potential jailbreaks -- malicious prompts that can disable the safety mechanism of LLMs -- has attracted growing…

Cryptography and Security · Computer Science 2024-08-08 Jiahao Zhang , Zilong Wang , Ruofan Wang , Xingjun Ma , Yu-Gang Jiang

Diffusion Large Language Models (DLLMs) are emerging as a powerful alternative to the dominant Autoregressive Large Language Models, offering efficient parallel generation and capable global context modeling. However, the practical…

Computation and Language · Computer Science 2025-08-19 Jinsong Li , Xiaoyi Dong , Yuhang Zang , Yuhang Cao , Jiaqi Wang , Dahua Lin

Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due to their non-sequential decoding. Unlike autoregressive…

Machine Learning · Computer Science 2025-10-06 Linyu Wu , Linhao Zhong , Wenjie Qu , Yuexin Li , Yue Liu , Shengfang Zhai , Chunhua Shen , Jiaheng Zhang

Large language models (LLMs), known for their capability in understanding and following instructions, are vulnerable to adversarial attacks. Researchers have found that current commercial LLMs either fail to be "harmless" by presenting…

Cryptography and Security · Computer Science 2023-10-05 Bocheng Chen , Advait Paliwal , Qiben Yan

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning and text generation. However, these models can inadvertently generate unsafe or biased responses when prompted with problematic inputs, raising…

Computation and Language · Computer Science 2024-12-03 Avinash Amballa , Durga Sandeep Saluru , Gayathri Akkinapalli , Abhishek Sureddy , Akshay Kumar Sureddy

Safety, security, and compliance are essential requirements when aligning large language models (LLMs). However, many seemingly aligned LLMs are soon shown to be susceptible to jailbreak attacks. These attacks aim to circumvent the models'…

Cryptography and Security · Computer Science 2025-06-05 Chen Xiong , Xiangyu Qi , Pin-Yu Chen , Tsung-Yi Ho

Large language models (LLMs) have revolutionized the role of AI, yet pose potential social risks. To steer LLMs towards human preference, alignment technologies have been introduced and gained increasing attention. Nevertheless, existing…

Computation and Language · Computer Science 2024-10-01 Shitong Duan , Xiaoyuan Yi , Peng Zhang , Yan Liu , Zheng Liu , Tun Lu , Xing Xie , Ning Gu

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges…

Computation and Language · Computer Science 2025-05-30 Yi Luo , Zhenghao Lin , Yuhao Zhang , Jiashuo Sun , Chen Lin , Chengjin Xu , Xiangdong Su , Yelong Shen , Jian Guo , Yeyun Gong

Evaluating large language models (LLMs) today rests on fixed benchmarks that apply the same set of items to any model, producing ceiling and floor effects that mask capability gaps. We argue that the most informative evaluation signal lies…

Artificial Intelligence · Computer Science 2026-05-27 Haoxiang Wang , Da Yu , Huishuai Zhang

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Machine Learning · Computer Science 2026-01-28 Quy-Anh Dang , Chris Ngo

Large Language Models (LLMs) rely on safety alignment to obey safe requests while refusing harmful ones. However, traditional refusal mechanisms often lead to "rigid rejection," where a general template (e.g., "I cannot fulfill this…

Computation and Language · Computer Science 2026-05-11 Ying Zhang , Congyu Qiao , Xin Geng , Ning Xu
‹ Prev 1 3 4 5 6 7 10 Next ›