English
Related papers

Related papers: Gradient-Controlled Decoding: A Safety Guardrail f…

200 papers

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods, primarily designed for classification tasks, are ineffective…

Cryptography and Security · Computer Science 2025-11-12 Zihan Wang , Rui Zhang , Hongwei Li , Wenshu Fan , Wenbo Jiang , Qingchuan Zhao , Guowen Xu

Reinforcement learning (RL) fine-tuning transforms large language models while creating a vulnerability we experimentally verify: Our experiment shows that malicious RL fine-tuning dismantles safety guardrails with remarkable efficiency,…

Machine Learning · Computer Science 2025-05-08 Wenjun Cao

To enhance the safety of VLMs, this paper introduces a novel reasoning-based VLM guard model dubbed GuardReasoner-VL. The core idea is to incentivize the guard model to deliberatively reason before making moderation decisions via online RL.…

Artificial Intelligence · Computer Science 2025-05-19 Yue Liu , Shengfang Zhai , Mingzhe Du , Yulin Chen , Tri Cao , Hongcheng Gao , Cheng Wang , Xinfeng Li , Kun Wang , Junfeng Fang , Jiaheng Zhang , Bryan Hooi

As large language models (LLMs) are deployed in safety-critical settings, it is essential to ensure that their responses comply with safety standards. Prior research has revealed that LLMs often fail to grasp the notion of safe behaviors,…

Artificial Intelligence · Computer Science 2026-03-09 Kartik Sharma , Yiqiao Jin , Vineeth Rakesh , Yingtong Dou , Menghai Pan , Mahashweta Das , Srijan Kumar

Large Language Models (LLMs) are increasingly being integrated into services such as ChatGPT to provide responses to user queries. To mitigate potential harm and prevent misuse, there have been concerted efforts to align the LLMs with human…

Cryptography and Security · Computer Science 2024-12-30 Xiaomeng Hu , Pin-Yu Chen , Tsung-Yi Ho

Large Language Models (LLM) have made remarkable progress, but concerns about potential biases and harmful content persist. To address these apprehensions, we introduce a practical solution for ensuring LLM's safe and ethical use. Our novel…

Cryptography and Security · Computer Science 2025-04-24 Chaima Njeh , Haïfa Nakouri , Fehmi Jaafar

The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major safety measure is to proactively test the LLMs with…

Machine Learning · Computer Science 2025-11-10 Haibo Jin , Ruoxi Chen , Peiyan Zhang , Andy Zhou , Haohan Wang

Future beyond-5G and 6G systems demand ultra-reliable, low-latency communication with short blocklengths, motivating the development of universal decoding algorithms. Guessing decoding, which infers the noise or codeword candidate in order…

Information Theory · Computer Science 2025-11-24 Qianfan Wang , Jifan Liang , Peihong Yuan , Ken R. Duffy , Muriel Médard , Xiao Ma

Diffusion language models (DLMs) generate tokens in parallel through iterative denoising, which can reduce latency and enable bidirectional conditioning. However, the safety risks posed by jailbreak attacks that exploit this inference…

Artificial Intelligence · Computer Science 2026-02-18 Shojiro Yamabe , Jun Sakuma

Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly…

Computation and Language · Computer Science 2025-10-21 Masahiro Kaneko , Zeerak Talat , Timothy Baldwin

Multimodal Large Language Models (MLLMs) achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak attacks. While existing work focuses on explicit attacks, where malicious content resides in a single…

Cryptography and Security · Computer Science 2026-04-28 Xu Zhang , Hao Li , Zhichao Lu

Large language models (LLMs) are increasingly used to generate executable outputs, JSON objects, and API calls, where a single syntax error can make the output unusable. Constrained decoding enforces validity token-by-token via masking and…

Computation and Language · Computer Science 2026-03-05 Avinash Reddy , Thayne T. Walker , James S. Ide , Amrit Singh Bedi

Large language models (LLMs) achieve impressive performance across diverse tasks yet remain vulnerable to jailbreak attacks that bypass safety mechanisms. We present RAID (Refusal-Aware and Integrated Decoding), a framework that…

Computation and Language · Computer Science 2025-12-23 Tuan T. Nguyen , John Le , Thai T. Vu , Willy Susilo , Heath Cooper

Deploying large language models (LLMs) in real-world applications requires robust safety guard models to detect and block harmful user prompts. While large safety guard models achieve strong performance, their computational cost is…

Computation and Language · Computer Science 2025-05-23 Seanie Lee , Dong Bok Lee , Dominik Wagner , Minki Kang , Haebin Seong , Tobias Bocklet , Juho Lee , Sung Ju Hwang

The application of large language models to code generation has evolved from one-shot generation to iterative refinement, yet the evolution of security throughout iteration remains insufficiently understood. Through comparative experiments…

Cryptography and Security · Computer Science 2026-03-10 Yi Chen , Yun Bian , Haiquan Wang , Shihao Li , Zhe Cui

Text-to-Image models may generate harmful content, such as pornographic images, particularly when unsafe prompts are submitted. To address this issue, safety filters are often added on top of text-to-image models, or the models themselves…

Cryptography and Security · Computer Science 2026-01-09 Zhengyuan Jiang , Yuepeng Hu , Yuchen Yang , Yinzhi Cao , Neil Zhenqiang Gong

With the development of instruction-tuned large language models (LLMs), improving the safety of LLMs has become more critical. However, the current approaches for aligning the LLMs output with expected safety usually require substantial…

Computation and Language · Computer Science 2024-06-18 Qihuang Zhong , Liang Ding , Juhua Liu , Bo Du , Dacheng Tao

This paper introduces a tamper-resistant framework for large language models (LLMs) in medical applications, utilizing quantum gradient descent (QGD) to detect malicious parameter modifications in real time. Integrated into a LLaMA-based…

Molecular Networks · Quantitative Biology 2025-06-25 Fahmida Hai , Saif Nirzhor , Rubayat Khan , Don Roosan

As Large Language Models (LLMs) become increasingly integral to various domains, their potential to generate harmful responses has prompted significant societal and regulatory concerns. In response, governments have issued ethics guidelines…

Computation and Language · Computer Science 2026-05-12 Haibo Jin , Ruoxi Chen , Peiyan Zhang , Andy Zhou , Zelei Cheng , Haohan Wang

In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as "safeguards" or "guardrails", has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This…

Cryptography and Security · Computer Science 2024-06-06 Yi Dong , Ronghui Mu , Yanghao Zhang , Siqi Sun , Tianle Zhang , Changshun Wu , Gaojie Jin , Yi Qi , Jinwei Hu , Jie Meng , Saddek Bensalem , Xiaowei Huang
‹ Prev 1 8 9 10 Next ›