English
Related papers

Related papers: Fast Adversarial Attacks on Language Models In One…

200 papers

This paper documents early research conducted in 2022 on defending against prompt injection attacks in large language models, providing historical context for the evolution of this critical security domain. This research focuses on two…

Cryptography and Security · Computer Science 2025-09-19 Gustavo Sandoval , Denys Fenchenko , Junyao Chen

Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and safety implications of…

Cryptography and Security · Computer Science 2023-08-21 Xiangyu Qi , Kaixuan Huang , Ashwinee Panda , Peter Henderson , Mengdi Wang , Prateek Mittal

Recent advances in machine learning show that neural models are vulnerable to minimally perturbed inputs, or adversarial examples. Adversarial algorithms are optimization problems that minimize the accuracy of ML models by perturbing…

Machine Learning · Computer Science 2022-05-20 Thomas Cilloni , Charles Walter , Charles Fleming

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

Existing attacks against multimodal language models (MLLMs) primarily communicate instructions through text accompanied by adversarial images. In contrast, we exploit the capabilities of MLLMs to interpret non-textual instructions,…

Cryptography and Security · Computer Science 2025-06-03 Jiahui Geng , Thy Thy Tran , Preslav Nakov , Iryna Gurevych

Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous driving and robotic manipulation. Recent research has…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Yichen Wang , Hangtao Zhang , Hewen Pan , Ziqi Zhou , Xianlong Wang , Peijin Guo , Lulu Xue , Shengshan Hu , Minghui Li , Leo Yu Zhang

Large language models (LLMs) are now highly capable at a diverse range of tasks. This paper studies whether or not GPT-4, one such LLM, is capable of assisting researchers in the field of adversarial machine learning. As a case study, we…

Cryptography and Security · Computer Science 2023-07-28 Nicholas Carlini

Mainstream backdoor attacks on large language models (LLMs) typically set a fixed trigger in the input instance and specific responses for triggered queries. However, the fixed trigger setting (e.g., unusual words) may be easily detected by…

Computation and Language · Computer Science 2025-01-09 Jiaming He , Wenbo Jiang , Guanyu Hou , Wenshu Fan , Rui Zhang , Hongwei Li

Multimodal large language models (MLLMs) have achieved remarkable progress, yet remain critically vulnerable to adversarial attacks that exploit weaknesses in cross-modal processing. We present a systematic study of multimodal jailbreaks…

Cryptography and Security · Computer Science 2025-10-24 Divyanshu Kumar , Shreyas Jena , Nitin Aravind Birur , Tanay Baswa , Sahil Agarwal , Prashanth Harshangi

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Cryptography and Security · Computer Science 2023-07-28 Nikhil Kandpal , Matthew Jagielski , Florian Tramèr , Nicholas Carlini

Many deep learning models have achieved dominant performance on the offline beat tracking task. However, online beat tracking, in which only the past and present input features are available, still remains challenging. In this paper, we…

Sound · Computer Science 2024-04-24 Chih-Cheng Chang , Li Su

Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extensive research in…

Artificial Intelligence · Computer Science 2023-06-30 Edoardo Mosca , Shreyash Agarwal , Javier Rando , Georg Groh

Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs. However, such vision-driven embodied agents open a new attack…

Artificial Intelligence · Computer Science 2026-02-24 Qiusi Zhan , Hyeonjeong Ha , Rui Yang , Sirui Xu , Hanyang Chen , Liang-Yan Gui , Yu-Xiong Wang , Huan Zhang , Heng Ji , Daniel Kang

As advances in Deep Neural Networks (DNNs) demonstrate unprecedented levels of performance in many critical applications, their vulnerability to attacks is still an open question. We consider evasion attacks at testing time against Deep…

Cryptography and Security · Computer Science 2022-06-16 Alesia Chernikova , Alina Oprea

We study adversarial attacks on linear stochastic bandits: by manipulating the rewards, an adversary aims to control the behaviour of the bandit algorithm. Perhaps surprisingly, we first show that some attack goals can never be achieved.…

Machine Learning · Computer Science 2022-07-05 Huazheng Wang , Haifeng Xu , Hongning Wang

Large Language Models (LLMs) have demonstrated remarkable capabilities in generating coherent text but remain limited by the static nature of their training data. Retrieval Augmented Generation (RAG) addresses this issue by combining LLMs…

Cryptography and Security · Computer Science 2024-10-21 Cody Clop , Yannick Teglia

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial…

Computation and Language · Computer Science 2026-05-25 Jinyang Wu , Bin Zhu , Xiandong Zou , Qiquan Zhang , Xu Fang , Pan Zhou

Recent researches have shown that Large Language Models (LLMs) are susceptible to a security threat known as Backdoor Attack. The backdoored model will behave well in normal cases but exhibit malicious behaviours on inputs inserted with a…

Cryptography and Security · Computer Science 2024-04-04 Yunzhuo Hao , Wenkai Yang , Yankai Lin

Recent advances in deep learning research have shown remarkable achievements across many tasks in computer vision (CV) and natural language processing (NLP). At the intersection of CV and NLP is the problem of image captioning, where the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Jiyao Li , Mingze Ni , Yifei Dong , Tianqing Zhu , Wei Liu

Recent advances in Vision-Language Models (VLMs) have greatly enhanced the integration of visual perception and linguistic reasoning, driving rapid progress in multimodal understanding. Despite these achievements, the security of VLMs,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Nam Duong Tran , Phi Le Nguyen