English
Related papers

Related papers: Jailbreak in pieces: Compositional Adversarial Att…

200 papers

We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as VLMs serve as the perceptual backbone of autonomous agents,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Ravikumar Balakrishnan , Sanket Mendapara , Ankit Garg

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

Computation and Language · Computer Science 2023-10-18 Erfan Shayegani , Md Abdullah Al Mamun , Yu Fu , Pedram Zaree , Yue Dong , Nael Abu-Ghazaleh

Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, LLMs still tend to generate harmful responses when faced with malicious instructions, a phenomenon referred to as "Jailbreak…

Computation and Language · Computer Science 2024-02-26 Yanrui Du , Sendong Zhao , Ming Ma , Yuhan Chen , Bing Qin

Despite their superior performance on a wide range of domains, large language models (LLMs) remain vulnerable to misuse for generating harmful content, a risk that has been further amplified by various jailbreak attacks. Existing jailbreak…

Cryptography and Security · Computer Science 2025-10-27 Yukun Jiang , Mingjie Li , Michael Backes , Yang Zhang

Language models are highly sensitive to prompt formulations - small changes in input can drastically alter their output. This raises a critical question: To what extent can prompt sensitivity be exploited to generate inapt content? In this…

Computation and Language · Computer Science 2025-07-21 Palash Nandi , Maithili Joshi , Tanmoy Chakraborty

The field of adversarial robustness has long established that adversarial examples can successfully transfer between image classifiers and that text jailbreaks can successfully transfer between language models (LMs). However, a pair of…

Machine Learning · Computer Science 2025-10-06 Isha Gupta , Rylan Schaeffer , Joshua Kazdan , Ken Ziyu Liu , Sanmi Koyejo

Text-to-image generative models are widely deployed in creative tools and online platforms. To mitigate misuse, these systems rely on safety filters and moderation pipelines that aim to block harmful or policy violating content. In this…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Ahmed B Mustafa , Zihan Ye , Yang Lu , Michael P Pound , Shreyank N Gowda

Defense in large language models (LLMs) is crucial to counter the numerous attackers exploiting these systems to generate harmful content through manipulated prompts, known as jailbreak attacks. Although many defense strategies have been…

Cryptography and Security · Computer Science 2024-12-11 Bocheng Chen , Hanqing Guo , Qiben Yan

It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. In this work, we argue that the spectrum of adversarial attacks on LLMs is much larger than merely…

Machine Learning · Computer Science 2024-02-22 Jonas Geiping , Alex Stein , Manli Shu , Khalid Saifullah , Yuxin Wen , Tom Goldstein

Current studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks. However, they overlook that the direct generation of harmful content from scratch is more difficult than inducing LLM to…

Computation and Language · Computer Science 2026-02-12 Yu Yan , Sheng Sun , Zenghao Duan , Teli Liu , Min Liu , Zhiyi Yin , Jingyu Lei , Qi Li

Metaphor serves as an implicit approach to convey information, while enabling the generalized comprehension of complex subjects. However, metaphor can potentially be exploited to bypass the safety alignment mechanisms of Large Language…

Computation and Language · Computer Science 2025-02-25 Yu Yan , Sheng Sun , Junqi Tong , Min Liu , Qi Li

We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 frontier proprietary and open-weight models, curated poetic prompts yielded high attack-success…

As audio-visual multi-modal large language models (MLLMs) are increasingly deployed in safety-critical applications, understanding their vulnerabilities is crucial. To this end, we introduce Multi-Modal Typography, a systematic study…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Tianle Chen , Deepti Ghadiyaram

Large Language Models (LLMs) are susceptible to Jailbreaking attacks, which aim to extract harmful information by subtly modifying the attack query. As defense mechanisms evolve, directly obtaining harmful information becomes increasingly…

Machine Learning · Computer Science 2024-10-03 Yixin Cheng , Markos Georgopoulos , Volkan Cevher , Grigorios G. Chrysos

As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone and an expanded attack surface. SLMs have been previously shown to be susceptible to jailbreaking, where…

Machine Learning · Computer Science 2026-03-20 Aravind Krishnan , Karolina Stańczak , Dietrich Klakow

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new…

Machine Learning · Computer Science 2025-06-26 Mahdi Sabbaghi , Paul Kassianik , George Pappas , Yaron Singer , Amin Karbasi , Hamed Hassani

Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and formalize the inscriptive jailbreak, where an adversary coerces a T2I system into generating…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Zonghao Ying , Haowen Dai , Lianyu Hu , Zonglei Jing , Quanchen Zou , Yaodong Yang , Aishan Liu , Xianglong Liu

Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks and defenses exist, their cross-lingual generalization…

Computation and Language · Computer Science 2025-11-05 Berk Atil , Rebecca J. Passonneau , Fred Morstatter

In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…

Computation and Language · Computer Science 2025-04-18 Charlotte Siska , Anush Sankaran

In recent years, the security vulnerabilities of Multi-modal Large Language Models (MLLMs) have become a serious concern in the Generative Artificial Intelligence (GenAI) research. These highly intelligent models, capable of performing…

Cryptography and Security · Computer Science 2026-01-12 Badhan Chandra Das , Md Tasnim Jawad , Joaquin Molto , M. Hadi Amini , Yanzhao Wu