相关论文: Bilateral Dependency Optimization: Defending Again…

Offline reinforcement learning agents face significant deployment challenges due to the synthetic-to-real distribution mismatch. While most prior research has focused on improving the fidelity of synthetic sampling and incorporating…

We consider the theoretical problem of designing an optimal adversarial attack on a decision system that maximally degrades the achievable performance of the system as measured by the mutual information between the degraded signal and the…

Deep Neural Networks (DNNs) have revolutionized various domains with their exceptional performance across numerous applications. However, Model Inversion (MI) attacks, which disclose private information about the training dataset by abusing…

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning…

Operating in a dynamic real world environment requires a forward thinking and adversarial aware design for classifiers, beyond fitting the model to the training data. In such scenarios, it is necessary to make classifiers - a) harder to…

We theoretically analyse the limits of robustness to test-time adversarial and noisy examples in classification. Our work focuses on deriving bounds which uniformly apply to all classifiers (i.e all measurable functions from features to…

This study investigates behavior-targeted attacks on reinforcement learning and their countermeasures. Behavior-targeted attacks aim to manipulate the victim's behavior as desired by the adversary through adversarial interventions in state…

Federated learning is a technique that allows multiple entities to collaboratively train models using their data without compromising data privacy. However, despite its advantages, federated learning can be susceptible to false data…

As a privacy-preserving method for implementing Vertical Federated Learning, Split Learning has been extensively researched. However, numerous studies have indicated that the privacy-preserving capability of Split Learning is insufficient.…

The remarkable capabilities of Large Language Models (LLMs) have raised significant safety concerns, particularly regarding "jailbreak" attacks that exploit adversarial prompts to bypass safety alignment mechanisms. Existing defense…

Machine learning is becoming increasingly popular as a go-to approach for many tasks due to its world-class results. As a result, antivirus developers are incorporating machine learning models into their products. While these models improve…

Minimizing risk with fairness constraints is one of the popular approaches to learning a fair classifier. Recent works showed that this approach yields an unfair classifier if the training set is corrupted. In this work, we study the…

Offline model-based optimization (MBO) seeks to discover high-performing designs using only a fixed dataset of past evaluations. Most existing methods rely on learning a surrogate model via regression and implicitly assume that good…

Split learning is a collaborative learning design that allows several participants (clients) to train a shared model while keeping their datasets private. Recent studies demonstrate that collaborative learning models, specifically federated…

Machine learning (ML) is vulnerable to inference (e.g., membership inference, property inference, and data reconstruction) attacks that aim to infer the private information of training data or dataset. Existing defenses are only designed…

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…

Adversarial training was introduced as a way to improve the robustness of deep learning models to adversarial attacks. This training method improves robustness against adversarial attacks, but increases the models vulnerability to privacy…

While image-based detectors have shown promise in Android malware detection, they often struggle to maintain their performance and interpretability when encountering out-of-distribution (OOD) samples. Specifically, OOD samples generated by…

We introduce a novel machine unlearning framework founded upon the established principles of the min-max optimization paradigm. We capitalize on the capabilities of strong Membership Inference Attacks (MIA) to facilitate the unlearning of…

Heatmap-based solvers have emerged as a promising paradigm for Combinatorial Optimization (CO). However, we argue that the dominant Supervised Learning (SL) training paradigm suffers from a fundamental objective mismatch: minimizing…