FecalFace

説明 | インストール | Webサイト | 課題 FecalFace 説明 FecalFaceは「Shit Bucket」のコンセプトから生まれました。そのアイデアは、お互いが持つデータを腐らせようとするものです。 具体的には、顔の検出と認識に関連しています。 このプロジェクトの動機は、私たちの顔を収集する企業がもはや私たちを識別できないようにすることです。 このプロジェクト（現時点ではPoC）には以下が含まれます： 入力されたRRSSのアバター内の顔を検出する 自分のアカウントでそれらを識別する 敵対的入力攻撃を使用して保護する 識別なしでの検出を確認する...

attack-attention

有效攻击基础模型的注意力可有效扰乱下游任务 论文 "Attacking Attention of Foundation Models Effectively Disrupts Downstream Tasks" 的官方 PyTorch 实现，已被 CVPR 2025 的 ADVML （对抗性机器学习在计算机视觉中的应用：基础模型 + X）研讨会接收。 有效攻击基础模型的注意力可有效扰乱下游任务" Hondamunige Prasanna Silva、Federico Becattini 和 Lorenzo Seidenari 摘要：...

Defenses-for-Tool-Integrated-LLM

面向工具集成式 LLM 智能体的通用防御：抵御对抗性攻击 本仓库包含我们项目的代码与实验，该项目旨在防御工具集成式大型语言模型（LLM）智能体免受对抗性攻击。 概述 我们基于 Agent Security Bench（ASB）构建，评估集成工具与结构化推理（例如思维链、反思）如何影响 LLM 智能体在多种任务场景下对对抗性提示的脆弱性。 本仓库包含： 新的防御策略（例如基于工具的过滤、CoT+Reflection） 改编自 ASB 的攻击场景 实验脚本 基于 Agent Security Bench（ASB） 本项目改编并扩展 了官方 ASB 仓库的代码： Agent Security...

Explainability-Guided Adversarial Attacks on Transformer-Based Malware Detectors Using Control Flow Graphs

Transformer-based malware detection systems operating on graph modalities such as control flow graphs CFGs achieve strong performance by modeling structural relationships in program behavior. However, their robustness to adversarial evasion attacks remains underexplored. This paper examines the...

Recovery-Induced Erasure Attack on QKD Systems

Detector dead time is typically treated as a fixed parameter in quantum key distribution QKD security analyses. In practice, however, the effective recovery time of single-photon avalanche photodiodes SPADs depends on the incident count rate. In this work, we demonstrate that this...

The Role of Learning in Attacking Intrusion Detection Systems

Recent work on network attacks have demonstrated that ML-based network intrusion detection systems NIDS can be evaded with adversarial perturbations. However, these attacks rely on complex optimizations that have large computational overheads, making them impractical in many real-world settings. ...

Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack

Audio-language models combine audio encoders with large language models to enable multimodal reasoning, but they also introduce new security vulnerabilities. We propose a universal targeted latent space attack, an encoder-level adversarial attack that manipulates audio latent representations to...

LLM-Driven Feature-Level Adversarial Attacks on Android Malware Detectors

The rapid growth in both the scale and complexity of Android malware has driven the widespread adoption of machine learning ML techniques for scalable and accurate malware detection. Despite their effectiveness, these models remain vulnerable to adversarial attacks that introduce carefully crafte...

IoT-Based Android Malware Detection Using Graph Neural Network with Adversarial Defense

Since the Internet of Things IoT is widely adopted using Android applications, detecting malicious Android apps is essential. In recent years, Android graph-based deep learning research has proposed many approaches to extract relationships from applications as graphs to generate graph embeddings...

A Novel and Practical Universal Adversarial Perturbations against Deep Reinforcement Learning Based Intrusion Detection Systems

Intrusion Detection Systems IDS play a vital role in defending modern cyber physical systems against increasingly sophisticated cyber threats. Deep Reinforcement Learning-based IDS, have shown promise due to their adaptive and generalization capabilities. However, recent studies reveal their...

GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs

Text-attributed graphs TAGs, which combine structural and textual node information, are ubiquitous across many domains. Recent work integrates Large Language Models LLMs with Graph Neural Networks GNNs to jointly model semantics and structure, resulting in more general and expressive models that...

Colliding with Adversaries at ECML-PKDD 2025 Adversarial Attack Competition 1st Prize Solution

This report presents the winning solution for Task 1 of Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics Discovery at ECML-PKDD 2025. The task required designing an adversarial attack against a provided classification model that maximizes misclassification while...

NatGVD: Natural Adversarial Example Attack Towards Graph-Based Vulnerability Detection

Graph-based models learn rich code graph structural information and present superior performance on various code analysis tasks. However, the robustness of these models against adversarial example attacks in the context of vulnerability detection remains an open question. This paper proposes...

A Practical Adversarial Attack against Sequence-Based Deep Learning Malware Classifiers

Sequence-based deep learning models e.g., RNNs, can detect malware by analyzing its behavioral sequences. Meanwhile, these models are susceptible to adversarial attacks. Attackers can create adversarial samples that alter the sequence characteristics of behavior sequences to deceive malware...

Between a Rock and a Hard Place: Exploiting Ethical Reasoning to Jailbreak LLMs

Large language models LLMs have undergone safety alignment efforts to mitigate harmful outputs. However, as LLMs become more sophisticated in reasoning, their intelligence may introduce new security risks. While traditional jailbreak attacks relied on singlestep attacks, multi-turn jailbreak...

ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models

Machine unlearning MU removes specific data points or concepts from deep learning models to enhance privacy and prevent sensitive content generation. Adversarial prompts can exploit unlearned models to generate content containing removed concepts, posing a significant security risk. However,...

Radio Adversarial Attacks on EMG-Based Gesture Recognition Networks

Surface electromyography EMG enables non-invasive human-computer interaction in rehabilitation, prosthetics, and virtual reality. While deep learning models achieve over 97% classification accuracy, their vulnerability to adversarial attacks remains largely unexplored in the physical domain. We...

Generating Adversarial Point Clouds Using Diffusion Model

Adversarial attack methods for 3D point cloud classification reveal the vulnerabilities of point cloud recognition models. This vulnerability could lead to safety risks in critical applications that use deep learning models, such as autonomous vehicles. To uncover the deficiencies of these models...

Scaling Decentralized Learning with FLock

Fine-tuning the large language models LLMs are prevented by the deficiency of centralized control and the massive computing and communication overhead on the decentralized schemes. While the typical standard federated learning FL supports data privacy, the central server requirement creates a...

Breaking the Illusion of Security Via Interpretation: Interpretable Vision Transformer Systems under Attack

Vision transformer ViT models, when coupled with interpretation models, are regarded as secure and challenging to deceive, making them well-suited for security-critical domains such as medical applications, autonomous vehicles, drones, and robotics. However, successful attacks on these systems ca...