English
Related papers

Related papers: Merging Improves Self-Critique Against Jailbreak A…

200 papers

This paper introduces MetaDefense, a novel framework for defending against finetuning-based jailbreak attacks in large language models (LLMs). We observe that existing defense mechanisms fail to generalize to harmful queries disguised by…

Machine Learning · Computer Science 2025-10-10 Weisen Jiang , Sinno Jialin Pan

While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after…

Computation and Language · Computer Science 2024-03-01 Nan Xu , Fei Wang , Ben Zhou , Bang Zheng Li , Chaowei Xiao , Muhao Chen

We present a novel approach for attacking black-box large language models (LLMs) by exploiting their ability to express confidence in natural language. Existing black-box attacks require either access to continuous model outputs like logits…

Cryptography and Security · Computer Science 2025-10-21 Jie Zhang , Meng Ding , Yang Liu , Jue Hong , Florian Tramèr

We propose a self-correction mechanism for Large Language Models (LLMs) to mitigate issues such as toxicity and fact hallucination. This method involves refining model outputs through an ensemble of critics and the model's own feedback.…

Large Language Models (LLMs) are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-aligned LLMs, they typically have limitations, such as…

Machine Learning · Computer Science 2026-03-11 Jesson Wang , Zhanhao Hu , David Wagner

Large Language Models (LLMs) have emerged as powerful re-rankers. Recent research has however showed that simple prompt injections embedded within a candidate document (i.e., jailbreak prompt attacks) can significantly alter an LLM's…

Cryptography and Security · Computer Science 2026-02-20 Yu Yin , Shuai Wang , Bevan Koopman , Guido Zuccon

We introduce new jailbreak attacks on vision language models (VLMs), which use aligned LLMs and are resilient to text-only jailbreak attacks. Specifically, we develop cross-modality attacks on alignment where we pair adversarial images…

Cryptography and Security · Computer Science 2023-10-12 Erfan Shayegani , Yue Dong , Nael Abu-Ghazaleh

GPT-4V has attracted considerable attention due to its extraordinary capacity for integrating and processing multimodal information. At the same time, its ability of face recognition raises new safety concerns of privacy leakage. Despite…

Computation and Language · Computer Science 2024-08-26 Yuanwei Wu , Yue Huang , Yixin Liu , Xiang Li , Pan Zhou , Lichao Sun

In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerable to jailbreak attacks, where adversaries can induce the…

Cryptography and Security · Computer Science 2024-08-23 Jiawei Zhao , Kejiang Chen , Xiaojian Yuan , Weiming Zhang

We discuss the ``Infinitely Many Paraphrases'' attacks (IMP), a category of jailbreaks that leverages the increasing capabilities of a model to handle paraphrases and encoded communications to bypass their defensive mechanisms. IMPs'…

Machine Learning · Computer Science 2025-03-14 Oliver Goldstein , Emanuele La Malfa , Felix Drinkall , Samuele Marro , Michael Wooldridge

Jailbreak attacks on large language models (LLMs) aim to induce LLMs to produce content that they are expected to refuse. Automated black-box jailbreak generation is especially important for safety evaluation, where the attacker observes…

Cryptography and Security · Computer Science 2026-05-29 Junke Zhang , Jianwei Wang , Sishuo Chen , Yizhang He , Qingshuai Feng , Zhengyi Yang

Large Language Models (LLMs) have achieved remarkable success in various domains but remain vulnerable to adversarial jailbreak attacks. Existing prompt-defense strategies, including parameter-modifying and parameter-free approaches, face…

Cryptography and Security · Computer Science 2025-02-20 Ziyi Ni , Hao Wang , Huacan Wang

Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns. However, the increasing size of these models…

Computation and Language · Computer Science 2024-04-19 Jiabao Ji , Bairu Hou , Zhen Zhang , Guanhua Zhang , Wenqi Fan , Qing Li , Yang Zhang , Gaowen Liu , Sijia Liu , Shiyu Chang

As LLMs develop increasingly advanced capabilities, there is an increased need to minimize the harm that could be caused to society by certain model outputs; hence, most LLMs have safety guardrails added, for example via fine-tuning. In…

Cryptography and Security · Computer Science 2025-01-22 David Williams-King , Linh Le , Adam Oberman , Yoshua Bengio

Large language models (LLMs) have been increasingly applied to various domains, which triggers increasing concerns about LLMs' safety on specialized domains, e.g. medicine. Despite prior explorations on general jailbreaking attacks, there…

Computation and Language · Computer Science 2025-06-10 Shangqing Tu , Zhuoran Pan , Wenxuan Wang , Zhexin Zhang , Yuliang Sun , Jifan Yu , Hongning Wang , Lei Hou , Juanzi Li

In the era of rapid generative AI development, interactions with large language models (LLMs) pose increasing risks of misuse. Prior research has primarily focused on attacks using template-based prompts and optimization-oriented methods,…

Cryptography and Security · Computer Science 2026-03-03 Wenhan Chang , Tianqing Zhu , Yu Zhao , Shuangyong Song , Ping Xiong , Wanlei Zhou

Security concerns for large language models (LLMs) have recently escalated, focusing on thwarting jailbreaking attempts in discrete prompts. However, the exploration of jailbreak vulnerabilities arising from continuous embeddings has been…

Cryptography and Security · Computer Science 2024-07-22 Zihao Xu , Yi Liu , Gelei Deng , Kailong Wang , Yuekang Li , Ling Shi , Stjepan Picek

Multimodal Large Language Models (MLLMs) have achieved impressive performance and have been put into practical use in commercial applications, but they still have potential safety mechanism vulnerabilities. Jailbreak attacks are red teaming…

Cryptography and Security · Computer Science 2025-06-30 Shiji Zhao , Ranjie Duan , Fengxiang Wang , Chi Chen , Caixin Kang , Shouwei Ruan , Jialing Tao , YueFeng Chen , Hui Xue , Xingxing Wei

Self-critic has become a crucial mechanism for enhancing the reasoning performance of LLMs. However, current approaches mainly involve basic prompts for intuitive instance-level feedback, which resembles System-1 processes and limits the…

Computation and Language · Computer Science 2025-06-12 Xin Zheng , Jie Lou , Boxi Cao , Xueru Wen , Yuqiu Ji , Hongyu Lin , Yaojie Lu , Xianpei Han , Debing Zhang , Le Sun

Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-17 Amirbek Djanibekov , Nurdaulet Mukhituly , Kentaro Inui , Hanan Aldarmaki , Nils Lukas
‹ Prev 1 8 9 10 Next ›