Colored Noise Injection for Training Adversarially Robust Neural Networks

论随机化在对抗鲁棒分类中的作用

On the Role of Randomization in Adversarially Robust Classification

本文厘清随机化在对抗鲁棒分类中的作用，证明随机化集成在特定条件下可优于确定性假设集，同时证明任何概率二分类器都存在更优的确定性分类器，并给出相应确定性假设集的显式描述。

基于自适应欺诈者检测的对抗鲁棒推荐研究

Towards Adversarially Robust Recommendation from Adaptive Fraudster Detection

针对推荐系统在节点注入攻击下的鲁棒性问题，提出明确考虑标签不确定性的自适应欺诈者检测模块，构建鲁棒框架PDR，有效抵御投毒攻击MetaC并提升对抗鲁棒性。

理解对抗鲁棒剪枝模型的容错性

Understanding Fault Tolerance of Adversarially Robust Pruned Models

该研究探究剪枝、对抗训练与硬件故障对CNN鲁棒性的交互影响，发现对抗训练提升抗扰动性但增权重故障敏感性，剪枝不显著增故障敏感性，需兼顾对抗鲁棒性与硬件可靠性。

Revisiting Adversarially Learned Injection Attacks Against Recommender Systems

Recommender systems play an important role in modern information and e-commerce applications. While increasing research is dedicated to improving the relevance and diversity of the recommendations, the potential risks of state-of-the-art recommendation models are under-explored, that is, these models could be subject to attacks from malicious third parties, through injecting fake user interactions to achieve their purposes. This paper revisits the adversarially-learned injection attack problem, where the injected fake user `behaviors' are learned locally by the attackers with their own model -…

Claudini: 自动研究发现针对LLM的最先进对抗攻击算法

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

本文提出一种自动研究循环，利用前沿AI代理（如Claude Code和Codex）自动发现针对大语言模型的新型对抗攻击算法，在白盒越狱和提示注入评估中达到最先进水平。

Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness

Mode connectivity provides novel geometric insights on analyzing loss landscapes and enables building high-accuracy pathways between well-trained neural networks. In this work, we propose to employ mode connectivity in loss landscapes to study the adversarial robustness of deep neural networks, and provide novel methods for improving this robustness. Our experiments cover various types of adversarial attacks applied to different network architectures and datasets. When network models are tampered with backdoor or error-injection attacks, our results demonstrate that the path connection learned…