English
Related papers

Related papers: Faster-GCG: Efficient Discrete Optimization Jailbr…

200 papers

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

The application of on-device language models (ODLMs) on resource-constrained edge devices is a multi-dimensional problem that strikes a fine balance between computational effectiveness, memory, power usage, and linguistic capacity across…

Computation and Language · Computer Science 2025-04-01 Basab Jha , Firoj Paudel

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and generation. However, these systems remain susceptible to malicious prompts that induce unsafe or policy-violating…

Machine Learning · Computer Science 2026-02-10 Shayan Ali Hassan , Tao Ni , Zafar Ayyub Qazi , Marco Canini

Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…

Cryptography and Security · Computer Science 2026-04-01 Md Jueal Mia , Joaquin Molto , Yanzhao Wu , M. Hadi Amini

Defending large language models (LLMs) against jailbreak attacks, such as Greedy Coordinate Gradient (GCG), remains a challenge, particularly under adaptive threat models where an attacker directly targets the defense mechanism. JBShield, a…

Cryptography and Security · Computer Science 2026-05-06 Kemal Derya , Berk Sunar

The scalability of Generalized Linear Models (GLMs) for large-scale, high-dimensional data often forces a trade-off between computational feasibility and statistical accuracy, particularly for inference on pre-specified parameters. While…

Methodology · Statistics 2025-12-09 Bo Fu , Dandan Jiang

Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended…

Computation and Language · Computer Science 2025-11-10 Chung-En Sun , Xiaodong Liu , Weiwei Yang , Tsui-Wei Weng , Hao Cheng , Aidan San , Michel Galley , Jianfeng Gao

Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…

Machine Learning · Computer Science 2026-02-10 Xuanqi Zhang , Haoyang Shang , Xiaoxiao Li

Ensuring safe, policy-compliant outputs from large language models requires real-time content moderation that can scale across multiple safety dimensions. However, state-of-the-art guardrail models rely on autoregressive decoders with…

Computation and Language · Computer Science 2026-05-11 Urchade Zaratiana , Mary Newhauser , George Hurn-Maloney , Ash Lewis

Jailbreak attacks reveal critical vulnerabilities in Large Language Models (LLMs) by causing them to generate harmful or unethical content. Evaluating these threats is particularly challenging due to the evolving nature of LLMs and the…

Machine Learning · Computer Science 2025-07-11 Peiyan Zhang , Haibo Jin , Liying Kang , Haohan Wang

Despite efforts to align large language models (LLMs) with human intentions, widely-used LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into generating objectionable…

Machine Learning · Computer Science 2024-06-17 Alexander Robey , Eric Wong , Hamed Hassani , George J. Pappas

Jailbreak attacks on audio language models (ALMs) optimize audio perturbations to elicit unsafe generations, and they typically update the entire waveform densely throughout optimization. In this work, we investigate the necessity of such…

Cryptography and Security · Computer Science 2026-05-26 Zheng Fang , Xiaosen Wang , Shenyi Zhang , Shaokang Wang , Zhijin Ge

While defenses against single-turn jailbreak attacks on Large Language Models (LLMs) have improved significantly, multi-turn jailbreaks remain a persistent vulnerability, often achieving success rates exceeding 70% against models optimized…

Machine Learning · Computer Science 2025-08-12 Xiaoxue Yang , Jaeha Lee , Anna-Katharina Dick , Jasper Timm , Fei Xie , Diogo Cruz

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

Computation and Language · Computer Science 2023-08-29 Huachuan Qiu , Shuai Zhang , Anqi Li , Hongliang He , Zhenzhong Lan

As the scale and complexity of jailbreaking attacks on large language models (LLMs) continue to escalate, their efficiency and practical applicability are constrained, posing a profound challenge to LLM security. Jailbreaking techniques…

Computation and Language · Computer Science 2025-12-23 Xiang Li , Chong Zhang , Jia Wang , Fangyu Wu , Yushi Li , Xiaobo Jin

Recently, Anil et al. (2024) show that many-shot (up to hundreds of) demonstrations can jailbreak state-of-the-art LLMs by exploiting their long-context capability. Nevertheless, is it possible to use few-shot demonstrations to efficiently…

Computation and Language · Computer Science 2024-10-31 Xiaosen Zheng , Tianyu Pang , Chao Du , Qian Liu , Jing Jiang , Min Lin

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Cryptography and Security · Computer Science 2025-09-09 Youjia Zheng , Mohammad Zandsalimy , Shanu Sushmita

Audio large language models (ALLMs) enable rich speech-text interaction, but they also introduce jailbreak vulnerabilities in the audio modality. Existing audio jailbreak methods mainly optimize jailbreak success while overlooking utility…

Sound · Computer Science 2026-04-13 Yunqiang Wang , Hengyuan Na , Di Wu , Miao Hu , Guocong Quan

Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by retrieving relevant documents from external corpora before generating responses. This approach significantly expands LLM capabilities by leveraging vast,…

Cryptography and Security · Computer Science 2025-11-13 Haowei Wang , Rupeng Zhang , Junjie Wang , Mingyang Li , Yuekai Huang , Dandan Wang , Qing Wang

Large Language Models~(LLMs) have demonstrated incredible capabilities in understanding, generating, and manipulating languages. Through human-model interactions, LLMs can automatically understand human-issued instructions and output the…

Computation and Language · Computer Science 2023-10-17 Haoke Zhang , Yue Wang , Juntao Li , Xiabing Zhou , Min Zhang