OpenAttack

문서 • 기능 및 사용 • 사용 예시 • 공격 모델 • 도구 키트 디자인 OpenAttack는 텍스트 적대적 공격adversarial attack의 전체 과정텍스트 전처리, 피해자 모델 접근, 적대적 예제 생성 및 평가을 처리하는 오픈소스 Python 기반 텍스트 적대적 공격 도구 키트입니다. 기능 및 사용 OpenAttack의 특징: ⭐️ 모든 공격 유형 지원. OpenAttack는 문장/단어/문자 수준의 변조perturbation 및 그래디언트/점수/결정 기반/블라인드 공격 모델 등 모든 유형의 공격을 지원합니다. ⭐️ 다국어...

foolbox

home: true heroImage: /logo.png heroText: Foolbox tagline: "Foolbox: PyTorch、TensorFlow、JAXで機械学習モデルの堅牢性をベンチマークするための高速な敵対的攻撃" actionText: 始める → actionLink: /guide/ features: title: ネイティブパフォーマンス details: Foolbox 3はEagerPy上に構築されており、PyTorch、TensorFlow、JAXでネイティブに動作します。 title: 最先端の攻撃 details:...

augustus

Augustus - LLM脆弱性スキャナー（プロンプトインジェクション、脱獄、敵対的攻撃テスト用） Augustus - LLM脆弱性スキャナー プロンプトインジェクション、脱獄、エンコーディング悪用、データ抽出をカバーする210以上の敵対的攻撃で大規模言語モデルをテストします。 Augustus は、セキュリティ専門家向けのGoベースのLLM脆弱性スキャナーです。幅広い敵対的攻撃に対して大規模言語モデルをテストし、28のLLMプロバイダーと統合し、実用的な脆弱性レポートを生成します。...

Awesome-MoAI-Security

Awesome Mobile On-Device AI Security SoK: Attack and Defense Landscape of Mobile On-device AI Systems 모바일 온디바이스 AI 시스템은 LiteRT/TFLite , Core ML , ExecuTorch , ONNX 와 같은 ML 프레임워크와 하드웨어 기반 가속기를 통해 AI 모델을 로컬에서 실행합니다. 이 저장소는 온디바이스 모델의 로컬 저장이 새로운 보안 위험을 도입함에 따라, 이러한 시스템을 이해하고 보호하는 데 필요한 보안 연구를 추적합니다...

Johnny Still Receives Spam SMS: Assessing the Robustness of SMS Spam Detection

SMS spam detection systems often achieve high accuracy in controlled environments but struggle against adversarial attacks and increasingly sophisticated spam tactics in real-world deployments. In this paper, we evaluate the robustness of SMS anti-spam systems that end users actually rely on,...

Categorical Robustness Assessment for Machine Learning Based Network Intrusion Detection Systems

Network Intrusion Detection Systems NIDS heavily utlize Machine Learning ML but ML models can be manipulated via adversarial attacks. These attacks add carefully crafted perturbations to network traffic data that leads to misclassifications. While prior work has demonstrated adversarial...

Context-Based Adversarial Attacks on AI Code Generators: Vulnerability Analysis and Implications

AI-powered code generation systems have transformed software development but introduce critical inference-time security vulnerabilities. This research presents a systematic investigation of context-based adversarial attacks, where strategically crafted contextual inputs, including comments,...

Protecting On-Device AI Inference: A Systematic Review of Attacks and Defence Mechanisms

The need for secure and private Artificial Intelligence AI and Machine Learning ML on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an ever-increasing number of pre-trained AI models being used o...

Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models

Large language models LLMs increasingly rely on explicit chain-of-thought CoT reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work on LLM safety focuses on content safety--detecting harmful, biased, or factually incorrect...

Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks

Retrieval-Augmented Generation RAG significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases. However, the multi-module architecture of RAG introduces complex system-level security vulnerabilities. Guided by the R...

Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks

Adversarial examples can represent a serious threat to machine learning ML algorithms. If used to manipulate the behaviour of ML-based Network Intrusion Detection Systems NIDS, they can jeopardize network security. In this work, we aim to mitigate such risks by increasing the robustness of NIDS...

Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection

The rise of bot accounts on social media poses significant risks to public discourse. To address this threat, modern bot detectors increasingly rely on Graph Neural Networks GNNs. However, the effectiveness of these GNN-based detectors in real-world settings remains poorly understood. In practice...

AI-Driven Cybersecurity Threats: A Survey of Emerging Risks and Defensive Strategies

Artificial Intelligence's dual-use nature is revolutionizing the cybersecurity landscape, introducing new threats across four main categories: deepfakes and synthetic media, adversarial AI attacks, automated malware, and AI-powered social engineering. This paper aims to analyze emerging risks,...

Enhancing Adversarial Robustness of IoT Intrusion Detection Via SHAP-Based Attribution Fingerprinting

The rapid proliferation of Internet of Things IoT devices has transformed numerous industries by enabling seamless connectivity and data-driven automation. However, this expansion has also exposed IoT networks to increasingly sophisticated security threats, including adversarial attacks targeting...

Quantifying the Risk of Transferred Black Box Attacks

Neural networks have become pervasive across various applications, including security-related products. However, their widespread adoption has heightened concerns regarding vulnerability to adversarial attacks. With emerging regulations and standards emphasizing security, organizations must...

Secure Control of Connected and Autonomous Electrified Vehicles under Adversarial Cyber-Attacks

Connected and Autonomous Electrified Vehicles CAEV is the solution to the future smart mobility having benefits of efficient traffic flow and cleaner environmental impact. Although CAEV has advantages they are still susceptible to adversarial cyber attacks due to their autonomous electric operati...

Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents

AI agents powered by large language models LLMs are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates security modeling, while the integration of traditional...

Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses

With the wide application of deep reinforcement learning DRL techniques in complex fields such as autonomous driving, intelligent manufacturing, and smart healthcare, how to improve its security and robustness in dynamic and changeable environments has become a core issue in current research...

Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models through Perceptually Simple Transformations

Multimodal large language models MLLMs have achieved remarkable progress, yet remain critically vulnerable to adversarial attacks that exploit weaknesses in cross-modal processing. We present a systematic study of multimodal jailbreaks targeting both vision-language and audio-language models,...

Exploring the Effect of DNN Depth on Adversarial Attacks in Network Intrusion Detection Systems

Adversarial attacks pose significant challenges to Machine Learning ML systems and especially Deep Neural Networks DNNs by subtly manipulating inputs to induce incorrect predictions. This paper investigates whether increasing the layer depth of deep neural networks affects their robustness agains...