Related papers: Understanding and Improving Continuous Adversarial…
Large language models (LLMs) remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies. While adversarial training can improve robustness, existing…
Research endeavors have been made in learning robust Multimodal Large Language Models (MLLMs) against jailbreak attacks. However, existing methods for improving MLLMs' robustness still face critical challenges: \ding{172} how to efficiently…
The security of Large Language Models (LLMs) has become an important research topic since the emergence of ChatGPT. Though there have been various effective methods to defend against jailbreak attacks, prefilling attacks remain an unsolved…
For years, adversarial training has been extensively studied in natural language processing (NLP) settings. The main goal is to make models robust so that similar inputs derive in semantically similar outcomes, which is not a trivial…
While multimodal large language models (MLLMs) have achieved remarkable success in recent advancements, their susceptibility to jailbreak attacks has come to light. In such attacks, adversaries exploit carefully crafted prompts to coerce…
Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples. However, most existing AT methods adopt a specific attack to craft adversarial examples,…
Many adversarial defense methods have been proposed to enhance the adversarial robustness of natural language processing models. However, most of them introduce additional pre-set linguistic knowledge and assume that the synonym candidates…
Deep Metric Learning (DML) has shown remarkable successes in many domains by taking advantage of powerful deep neural networks. Deep neural networks are prone to adversarial attacks and could be easily fooled by adversarial examples. The…
Generalization and robustness are both key desiderata for designing machine learning methods. Adversarial training can enhance robustness, but past work often finds it hurts generalization. In natural language processing (NLP), pre-training…
Adversarial training, which minimizes the maximal risk for label-preserving input perturbations, has proved to be effective for improving the generalization of language models. In this work, we propose a novel adversarial training…
Despite their impressive capabilities, Multimodal Large Language Models (MLLMs) exhibit perceptual fragility when confronted with visually complex scenes. This weakness stems from a reliance on finite training datasets, which are…
In real life, adversarial attack to deep learning models is a fatal security issue. However, the issue has been rarely discussed in a widely used class-incremental continual learning (CICL). In this paper, we address problems of applying…
Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the…
Large Language Models (LLMs) have achieved remarkable success in various domains but remain vulnerable to adversarial jailbreak attacks. Existing prompt-defense strategies, including parameter-modifying and parameter-free approaches, face…
Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…
In this work, we make two contributions towards understanding of in-context learning of linear models by transformers. First, we investigate the adversarial robustness of in-context learning in transformers to hijacking attacks -- a type of…
Large Language Models (LLMs) have demonstrated remarkable capabilities in performing tasks across various domains without needing explicit retraining. This capability, known as In-Context Learning (ICL), while impressive, exposes LLMs to a…
Large Language Models (LLMs) have shown remarkable success in various tasks, yet their safety and the risk of generating harmful content remain pressing concerns. In this paper, we delve into the potential of In-Context Learning (ICL) to…
Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the…
Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…