Related papers: A Classification-Guided Approach for Adversarial A…

Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbation can completely change prediction result. The vulnerability has led to a surge of research in this direction, including adversarial…

Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive…

Adversarial attacks in reinforcement learning (RL) often assume highly-privileged access to the victim's parameters, environment, or data. Instead, this paper proposes a novel adversarial setting called a Cheap Talk MDP in which an…

Recent studies have shown that deep neural networks are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. However,…

Adversarial training (AT) is a popular method for training robust deep neural networks (DNNs) against adversarial attacks. Yet, AT suffers from two shortcomings: (i) the robustness of DNNs trained by AT is highly intertwined with the size…

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,…

Adversarial training (AT) is an important and attractive topic in deep learning security, exhibiting mysteries and odd properties. Recent studies of neural network training dynamics based on Neural Tangent Kernel (NTK) make it possible to…

Class-incremental continual learning addresses catastrophic forgetting by enabling classification models to preserve knowledge of previously learned classes while acquiring new ones. However, the vulnerability of the models against…

Neural Machine Translation (NMT) has been widely adopted recently due to its advantages compared with the traditional Statistical Machine Translation (SMT). However, an NMT system still often produces translation failures due to the…

Neural ranking models (NRMs) have attracted considerable attention in information retrieval. Unfortunately, NRMs may inherit the adversarial vulnerabilities of general neural networks, which might be leveraged by black-hat search engine…

Although neural machine translation (NMT) has advanced the state-of-the-art on various language pairs, the interpretability of NMT remains unsatisfactory. In this work, we propose to address this gap by focusing on understanding the…

Multiple different approaches of generating adversarial examples have been proposed to attack deep neural networks. These approaches involve either directly computing gradients with respect to the image pixels, or directly solving an…

We show that hybrid quantum classifiers based on quantum kernel methods and support vector machines are vulnerable against adversarial attacks, namely small engineered perturbations of the input data can deceive the classifier into…

Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However,…

Adversarial examples --- perturbations to the input of a model that elicit large changes in the output --- have been shown to be an effective way of assessing the robustness of sequence-to-sequence (seq2seq) models. However, these…

Neural Machine Translation (NMT) has achieved significant breakthrough in performance but is known to suffer vulnerability to input perturbations. As real input noise is difficult to predict during training, robustness is a big issue for…

As the deployment of NLP systems in critical applications grows, ensuring the robustness of large language models (LLMs) against adversarial attacks becomes increasingly important. Large language models excel in various NLP tasks but remain…

Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness…

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

In targeted adversarial attacks on vision models, the selection of the target label is a critical yet often overlooked determinant of attack success. This target label corresponds to the class that the attacker aims to force the model to…