English
Related papers

Related papers: Disentangling Adversarial Prompts: A Semantic-Grap…

200 papers

Large Language Models (LLMs) have been equipped with safety mechanisms to prevent harmful outputs, but these guardrails can often be bypassed through "jailbreak" prompts. This paper introduces a novel graph-based approach to systematically…

Cryptography and Security · Computer Science 2025-04-18 Sinan He , An Wang

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs). A considerable amount of research exists proposing more effective jailbreak attacks, including the…

Cryptography and Security · Computer Science 2024-03-05 Daoyuan Wu , Shuai Wang , Yang Liu , Ning Liu

Large Language Models' safety remains a critical concern due to their vulnerability to adversarial attacks, which can prompt these systems to produce harmful responses. In the heart of these systems lies a safety classifier, a computational…

Computation and Language · Computer Science 2023-11-02 Jinhwa Kim , Ali Derakhshan , Ian G. Harris

The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common…

Computation and Language · Computer Science 2026-01-23 Rishit Chugh

The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…

Cryptography and Security · Computer Science 2024-12-10 Bryan Li , Sounak Bagchi , Zizhan Wang

Large language models (LLMs) are vulnerable to adversarial attacks that add malicious tokens to an input prompt to bypass the safety guardrails of an LLM and cause it to produce harmful content. In this work, we introduce erase-and-check,…

Computation and Language · Computer Science 2025-02-06 Aounon Kumar , Chirag Agarwal , Suraj Srinivas , Aaron Jiaxun Li , Soheil Feizi , Himabindu Lakkaraju

In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks predominantly focus on the visual modality, perturbing solely…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Zonghao Ying , Aishan Liu , Tianyuan Zhang , Zhengmin Yu , Siyuan Liang , Xianglong Liu , Dacheng Tao

Large language models (LLMs) remain vulnerable to jailbreak prompts that are fluent and semantically coherent, and therefore difficult to detect with standard heuristics. A particularly challenging failure mode occurs when an attacker tries…

Artificial Intelligence · Computer Science 2026-02-24 Amirhossein Farzam , Majid Behabahani , Mani Malek , Yuriy Nevmyvaka , Guillermo Sapiro

Adversarial prompts are capable of jailbreaking frontier large language models (LLMs) and inducing undesirable behaviours, posing a significant obstacle to their safe deployment. Current mitigation strategies primarily rely on activating…

Computation and Language · Computer Science 2025-10-08 Canaan Yung , Hanxun Huang , Christopher Leckie , Sarah Erfani

Advanced Persistent Threats (APTs) are among the most challenging cyberattacks to detect. They are carried out by highly skilled attackers who carefully study their targets and operate in a stealthy, long-term manner. Because APTs exhibit…

Large Language Model (LLM) applications are vulnerable to prompt injection and context manipulation attacks that traditional security models cannot prevent. We introduce two novel primitives--authenticated prompts and authenticated…

Cryptography and Security · Computer Science 2026-02-12 Mohan Rajagopalan , Vinay Rao

With the rapid advancement of multimodal learning, pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between visual and language modalities. However, these models remain…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Jiaming Zhang , Xingjun Ma , Xin Wang , Lingyu Qiu , Jiaqi Wang , Yu-Gang Jiang , Jitao Sang

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting prompts that induce LLMs to generate harmful content. Current methods…

Computation and Language · Computer Science 2025-10-21 Jiawei Lian , Jianhong Pan , Lefan Wang , Yi Wang , Shaohui Mei , Lap-Pui Chau

Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Lin Li , Haoyan Guan , Jianing Qiu , Michael Spratling

Large Language Models (LLMs) are increasingly being integrated into the scientific peer-review process, raising new questions about their reliability and resilience to manipulation. In this work, we investigate the potential for hidden…

Cryptography and Security · Computer Science 2026-03-31 Matteo Gioele Collu , Umberto Salviati , Roberto Confalonieri , Mauro Conti , Giovanni Apruzzese

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

Recent years have seen the wide application of NLP models in crucial areas such as finance, medical treatment, and news media, raising concerns of the model robustness and vulnerabilities. In this paper, we propose a novel prompt-based…

Computation and Language · Computer Science 2022-03-22 Yuting Yang , Pei Huang , Juan Cao , Jintao Li , Yun Lin , Jin Song Dong , Feifei Ma , Jian Zhang

Recently, Large Language Models (LLMs) have garnered significant attention for their exceptional natural language processing capabilities. However, concerns about their trustworthiness remain unresolved, particularly in addressing…

Computation and Language · Computer Science 2025-01-29 Yue Huang , Jingyu Tang , Dongping Chen , Bingda Tang , Yao Wan , Lichao Sun , Philip S. Yu , Xiangliang Zhang

The safety defense methods of Large language models(LLMs) stays limited because the dangerous prompts are manually curated to just few known attack types, which fails to keep pace with emerging varieties. Recent studies found that attaching…

Computation and Language · Computer Science 2024-06-05 Hao Wang , Hao Li , Minlie Huang , Lei Sha

Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perplexity-based detectors. We cast adversarial suffix detection as an online change-point…

Machine Learning · Computer Science 2026-05-20 Mohammed Alshaalan , Miguel R. D. Rodrigues