相关论文: Fighting Fire with Fire (F3): A Training-free and …

The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common…

Adversarial training, a method for learning robust deep neural networks, constructs adversarial examples during training. However, recent methods for generating NLP adversarial examples involve combinatorial search and expensive sentence…

Modern software relies on a multitude of automated testing and quality assurance tools to prevent errors, bugs and potential vulnerabilities. This study sets out to provide a head-to-head, quantitative and qualitative evaluation of six…

As the number of large language models (LLMs) released to the public grows, there is a pressing need to understand the safety implications associated with these models learning from third-party custom finetuning data. We explore the…

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…

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…

The increasing deployment of AI models in critical applications has exposed them to significant risks from adversarial attacks. While adversarial vulnerabilities in 2D vision models have been extensively studied, the threat landscape for 3D…

Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be…

Multimodal Large Language Models (MLLMs) often struggle to accurately perceive fine-grained visual details, especially when targets are tiny or visually subtle. This challenge can be addressed through semantic-visual information fusion,…

The generation of feasible adversarial examples is necessary for properly assessing models that work in constrained feature space. However, it remains a challenging task to enforce constraints into attacks that were designed for computer…

NLP models excel on tasks with clean inputs, but are less accurate with noisy inputs. In particular, character-level noise such as human-written typos and adversarially-engineered realistic-looking misspellings often appears in text and can…

Machine learning techniques are immensely deployed in both industry and academy. Recent studies indicate that machine learning models used for classification tasks are vulnerable to adversarial examples, which limits the usage of…

As machine learning models grow in complexity and increasingly rely on publicly sourced data, such as the human-annotated labels used in training large language models, they become more vulnerable to label poisoning attacks. These attacks,…

Defense models against adversarial attacks have grown significantly, but the lack of practical evaluation methods has hindered progress. Evaluation can be defined as looking for defense models' lower bound of robustness given a budget…

Although current deep learning techniques have yielded superior performance on various computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial training and its variants have been shown to be the most…

Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…

We propose a novel approach for generating unrestricted adversarial examples by manipulating fine-grained aspects of image generation. Unlike existing unrestricted attacks that typically hand-craft geometric transformations, we learn…

Adversarial purification refers to a class of defense methods that remove adversarial perturbations using a generative model. These methods do not make assumptions on the form of attack and the classification model, and thus can defend…

Adversarial training (AT) is widely considered the state-of-the-art technique for improving the robustness of deep neural networks (DNNs) against adversarial examples (AE). Nevertheless, recent studies have revealed that adversarially…

Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…