相关论文: Defense Against Model Extraction Attacks on Recomm…

Along with the advent of deep neural networks came various methods of exploitation, such as fooling the classifier or contaminating its training data. Another such attack is known as model extraction, where provided API access to some black…

Deep reinforcement learning has shown promising results in learning control policies for complex sequential decision-making tasks. However, these neural network-based policies are known to be vulnerable to adversarial examples. This…

We study the problem of robust reinforcement learning under adversarial corruption on both rewards and transitions. Our attack model assumes an \textit{adaptive} adversary who can arbitrarily corrupt the reward and transition at every step…

In recent years, machine learning algorithms have been applied widely in various fields such as health, transportation, and the autonomous car. With the rapid developments of deep learning techniques, it is critical to take the security…

Exploring effective and transferable adversarial examples is vital for understanding the characteristics and mechanisms of Vision Transformers (ViTs). However, adversarial examples generated from surrogate models often exhibit weak…

Neural ranking models (NRMs) have shown great success in information retrieval (IR). But their predictions can easily be manipulated using adversarial examples, which are crafted by adding imperceptible perturbations to legitimate…

Adversarial attacks, particularly the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) pose significant threats to the robustness of deep learning models in image classification. This paper explores and refines defense…

The vulnerability of Deep Neural Networks (DNNs) to adversarial examples has been confirmed. Existing adversarial defenses primarily aim at preventing adversarial examples from attacking DNNs successfully, rather than preventing their…

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…

Retrieval-Augmented Generation (RAG) is applied to solve hallucination problems and real-time constraints of large language models, but it also induces vulnerabilities against retrieval corruption attacks. Existing research mainly explores…

Model stealing (MS) involves querying and observing the output of a machine learning model to steal its capabilities. The quality of queried data is crucial, yet obtaining a large amount of real data for MS is often challenging. Recent…

Recent advances in large language models have highlighted the critical need for precise control over model outputs through predefined constraints. While existing methods attempt to achieve this through either direct instruction-response…

Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. Within these frameworks, the policy update relies on…

LLM-based ranking systems are vulnerable to Generative Engine Optimization (GEO) attacks, where adversaries inject semantic signals into product descriptions to artificially boost rankings. We propose SCI-Defense, a three-component defense…

Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturbations has moved from a peculiar phenomenon to a core issue in Deep Learning. Despite much attention, however, progress towards more robust…

Gradient-based attacks are important methods for evaluating model robustness. However, since the proposal of APGD, it has been difficult for such methods to achieve significant breakthroughs. To achieve such an effect, we first analyze the…

Adversarial attacks have exposed a significant security vulnerability in state-of-the-art machine learning models. Among these models include deep reinforcement learning agents. The existing methods for attacking reinforcement learning…

Direct optimization is an appealing framework that replaces integration with optimization of a random objective for approximating gradients in models with discrete random variables. A$^\star$ sampling is a framework for optimizing such…

Adversarial attacks present a critical challenge to deep neural networks' robustness, particularly in transfer scenarios across different model architectures. However, the transferability of adversarial attacks faces a fundamental dilemma…

Neural ranking models (NRMs) have achieved promising results in information retrieval. NRMs have also been shown to be vulnerable to adversarial examples. A typical Word Substitution Ranking Attack (WSRA) against NRMs was proposed recently,…