Related papers: Layer-Wise Perturbations via Sparse Autoencoders f…

While Large Language Models (LLMs) have achieved remarkable progress, they remain vulnerable to jailbreak attacks. Existing methods, primarily relying on discrete input optimization (e.g., GCG), often suffer from high computational costs…

The generation of toxic content by large language models (LLMs) remains a critical challenge for the safe deployment of language technology. We propose a novel framework for implicit knowledge editing and controlled text generation by…

We challenge the prevailing assumption that LLMs must rely fully on sub-word tokens for high-quality text generation. To this end, we propose the "Generative Pretrained Thoughtformer" (GPTHF), a hierarchical transformer language model…

The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create…

Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted results are accessible. Research on this…

Understanding the internal machinations of deep Transformer-based NLP models is more crucial than ever as these models see widespread use in various domains that affect the public at large, such as industry, academia, finance, health. While…

Large Language Models (LLMs) have impressive multilingual capabilities, but they suffer from unexpected code-switching, also known as language mixing, which involves switching to unexpected languages in the model response. This problem…

Adversarial training is the most empirically successful approach in improving the robustness of deep neural networks for image classification.For text classification, however, existing synonym substitution based adversarial attacks are…

We propose an adversarial defense method that achieves state-of-the-art performance among attack-agnostic adversarial defense methods while also maintaining robustness to input resolution, scale of adversarial perturbation, and scale of…

Deep convolutional neural networks are susceptible to adversarial attacks. They can be easily deceived to give an incorrect output by adding a tiny perturbation to the input. This presents a great challenge in making CNNs robust against…

As the development of deep learning techniques in autonomous landing systems continues to grow, one of the major challenges is trust and security in the face of possible adversarial attacks. In this paper, we propose a federated adversarial…

Deep learning models, while achieving state-of-the-art performance on many tasks, are susceptible to adversarial attacks that exploit inherent vulnerabilities in their architectures. Adversarial attacks manipulate the input data with…

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples. Adversarial examples are malicious images with visually imperceptible perturbations. While these carefully crafted perturbations restricted with tight…

Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers. These attacks, however, generally assume that the victim model is…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through additional training, we explore an alternative: steering model…

LLMs have shown impressive capabilities across various natural language processing tasks, yet remain vulnerable to input prompts, known as jailbreak attacks, carefully designed to bypass safety guardrails and elicit harmful responses.…

We present an adversarial framework to craft perturbations that mislead classifiers by accounting for the image content and the semantics of the labels. The proposed framework combines a structure loss and a semantic adversarial loss in a…

Deep learning models can be fooled by small $l_p$-norm adversarial perturbations and natural perturbations in terms of attributes. Although the robustness against each perturbation has been explored, it remains a challenge to address the…

Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a…