Related papers: Attacking Large Language Models with Projected Gra…
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…
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…
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…
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,…
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…
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…
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…
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…
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…
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.…
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…
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…
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…
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…
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…
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…
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…