相关论文: An Empirical Study of Aegis

An evolution strategy (ES) variant based on a simplification of a natural evolution strategy recently attracted attention because it performs surprisingly well in challenging deep reinforcement learning domains. It searches for neural…

There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has focused on studying weaknesses against evasion or poisoning…

Early exits enable the network's forward pass to terminate early by attaching trainable internal classifiers to the backbone network. Existing early-exit methods typically adopt either a joint training approach, where the backbone and exit…

The integration of Artificial Intelligence (AI) in Network Intrusion Detection Systems (NIDS) is a promising approach to tackle the increasing sophistication of cyberattacks. However, since Machine Learning (ML) and Deep Learning (DL)…

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…

Despite the striking successes of deep neural networks trained with gradient-based optimization, these methods differ fundamentally from their biological counterparts. This gap raises key questions about how nature achieves robust,…

The rise of foundation models fine-tuned on human feedback from potentially untrusted users has increased the risk of adversarial data poisoning, necessitating the study of robustness of learning algorithms against such attacks. Existing…

The existence of adversarial examples underscores the importance of understanding the robustness of machine learning models. Bayesian neural networks (BNNs), due to their calibrated uncertainty, have been shown to posses favorable…

This study investigates a counterintuitive phenomenon in adversarial machine learning: the potential for noise-based defenses to inadvertently aid evasion attacks in certain scenarios. While randomness is often employed as a defensive…

Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input $x$ and any target classification $t$, it is possible to find a new…

Spiking neural networks (SNNs) compute with discrete spikes and exploit temporal structure, yet most adversarial attacks change intensities or event counts instead of timing. We study a timing-only adversary that retimes existing spikes…

Adversarial defenses train deep neural networks to be invariant to the input perturbations from adversarial attacks. Almost all defense strategies achieve this invariance through adversarial training i.e. training on inputs with adversarial…

Despite its popularity, deep neural networks are easily fooled. To alleviate this deficiency, researchers are actively developing new training strategies, which encourage models that are robust to small input perturbations. Several…

A new approach on cryptanalysis is proposed where the goal is to explore the fundamental limits of a specific class of attacks against a particular cryptosystem. As a first step, the approach is applied on ABSG, which is an LFSR-based…

Deep models, while being extremely versatile and accurate, are vulnerable to adversarial attacks: slight perturbations that are imperceptible to humans can completely flip the prediction of deep models. Many attack and defense mechanisms…

Deep learning models have achieved great success in many fields, yet they are vulnerable to adversarial examples. This paper follows a causal perspective to look into the adversarial vulnerability and proposes Causal Intervention by…

The increasing access to data poses both opportunities and risks in deep learning, as one can manipulate the behaviors of deep learning models with malicious training samples. Such attacks are known as data poisoning. Recent advances in…

Adversarial Training (AT) is a cornerstone defense, but many variants overlook foundational feature representations by primarily focusing on stronger attack generation. We introduce Adversarial Evolution Training (AET), a simple yet…

Some recent works revealed that deep neural networks (DNNs) are vulnerable to so-called adversarial attacks where input examples are intentionally perturbed to fool DNNs. In this work, we revisit the DNN training process that includes…

Security challenges accompany the efficiency. The pervasive integration of information and communications technologies (ICTs) makes cyber-physical systems vulnerable to targeted attacks that are deceptive, persistent, adaptive and…