English
Related papers

Related papers: Attacking Large Language Models with Projected Gra…

200 papers

To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a…

There are two primary ways of incorporating new information into a language model (LM): changing its prompt or changing its parameters, e.g. via fine-tuning. Parameter updates incur no long-term storage cost for model changes. However, for…

Computation and Language · Computer Science 2025-06-27 Eric Zhang , Leshem Choshen , Jacob Andreas

Despite emerging research on Language Models (LM), few approaches analyse the invertibility of LMs. That is, given a LM and a desirable target output sequence of tokens, determining what input prompts would yield the target output remains…

Computation and Language · Computer Science 2026-02-12 Kevin Yandoka Denamganaï , Kartic Subr

The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs. These solutions facilitate tailored LLM creation via natural language prompts without coding. However, the trustworthiness…

Cryptography and Security · Computer Science 2024-05-29 Rui Zhang , Hongwei Li , Rui Wen , Wenbo Jiang , Yuan Zhang , Michael Backes , Yun Shen , Yang Zhang

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Machine Learning · Computer Science 2025-01-22 Qizhang Li , Xiaochen Yang , Wangmeng Zuo , Yiwen Guo

Prompt engineering has proven to be a crucial step in leveraging pretrained large language models (LLMs) in solving various real-world tasks. Numerous solutions have been proposed that seek to automate prompt engineering by using the model…

Adversarial training is the most successful empirical method for increasing the robustness of neural networks against adversarial attacks. However, the most effective approaches, like training with Projected Gradient Descent (PGD) are…

Machine Learning · Computer Science 2020-03-18 Leo Schwinn , René Raab , Björn Eskofier

Differentially Private (DP) learning has seen limited success for building large deep learning models of text, and straightforward attempts at applying Differentially Private Stochastic Gradient Descent (DP-SGD) to NLP tasks have resulted…

Machine Learning · Computer Science 2022-11-11 Xuechen Li , Florian Tramèr , Percy Liang , Tatsunori Hashimoto

We investigate adversarial-sample generation methods from a frequency domain perspective and extend standard $l_{\infty}$ Projected Gradient Descent (PGD) to the frequency domain. The resulting method, which we call Spectral Projected…

Machine Learning · Computer Science 2020-10-14 Hans Shih-Han Wang , Cory Cornelius , Brandon Edwards , Jason Martin

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

Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images. As one of the most…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Jindong Gu , Hengshuang Zhao , Volker Tresp , Philip Torr

Large language models (LLMs) have been widely adopted in applications such as automated content generation and even critical decision-making systems. However, the risk of prompt injection allows for potential manipulation of LLM outputs.…

Computation and Language · Computer Science 2024-11-25 Jiashuo Liang , Guancheng Li , Yang Yu

This work aims to investigate how different Large Language Models (LLMs) alignment methods affect the models' responses to prompt attacks. We selected open source models based on the most common alignment methods, namely, Supervised…

Deep learning-based natural language processing (NLP) models, particularly pre-trained language models (PLMs), have been revealed to be vulnerable to adversarial attacks. However, the adversarial examples generated by many mainstream…

Computation and Language · Computer Science 2023-11-21 Zimu Wang , Wei Wang , Qi Chen , Qiufeng Wang , Anh Nguyen

In this paper, we investigate the dynamics-aware adversarial attack problem in deep neural networks. Most existing adversarial attack algorithms are designed under a basic assumption -- the network architecture is fixed throughout the…

Computer Vision and Pattern Recognition · Computer Science 2023-01-24 An Tao , Yueqi Duan , He Wang , Ziyi Wu , Pengliang Ji , Haowen Sun , Jie Zhou , Jiwen Lu

LLM-based prompt optimization, that uses LLM-provided "textual gradients" (feedback) to refine prompts, has emerged an effective method for automatic prompt engineering. However, its scalability and stability are unclear when using more…

Computation and Language · Computer Science 2025-11-19 Zixin Ding , Junyuan Hong , Zhan Shi , Jiachen T. Wang , Zinan Lin , Li Yin , Meng Liu , Zhangyang Wang , Yuxin Chen

Advances in the development of adversarial attacks have been fundamental to the progress of adversarial defense research. Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust…

Computer Vision and Pattern Recognition · Computer Science 2020-12-01 Gaurang Sriramanan , Sravanti Addepalli , Arya Baburaj , R. Venkatesh Babu

In this paper, we investigate the dynamics-aware adversarial attack problem of adaptive neural networks. Most existing adversarial attack algorithms are designed under a basic assumption -- the network architecture is fixed throughout the…

Computer Vision and Pattern Recognition · Computer Science 2024-01-12 An Tao , Yueqi Duan , Yingqi Wang , Jiwen Lu , Jie Zhou

In recent years, Large Language Models (LLM) have emerged as pivotal tools in various applications. However, these models are susceptible to adversarial prompt attacks, where attackers can carefully curate input strings that mislead LLMs…

Computation and Language · Computer Science 2024-02-20 Zhengmian Hu , Gang Wu , Saayan Mitra , Ruiyi Zhang , Tong Sun , Heng Huang , Viswanathan Swaminathan

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…