🔒 Category

cs.CR

284 papers

Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local Executors

This paper proposes Survivability-Aware Execution (SAE), a middleware framework for OpenClaw-style agentic crypto trading systems that enforces non-bypassable invariants like exposure budgets and order-rate limits to mitigate execution-induced losses from untrusted prompts or compromised skills, demonstrating significant reductions in maximum drawdown and risk metrics through offline replay testing.

Ailiya Borjigin, Igor Stadnyk, Ben Bilski, Serhii Hovorov, Sofiia PidturkinaThu, 12 Ma🤖 cs.AI

Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance Vulnerabilities

This paper introduces the first systematic framework for identifying and exploiting "compatibility-abusing attacks" in the Model Context Protocol (MCP) by utilizing a language-agnostic intermediate representation and LLM-guided static analysis to uncover security vulnerabilities stemming from optional clause implementations across diverse SDKs.

Nanzi Yang, Weiheng Bai, Kangjie LuThu, 12 Ma🤖 cs.AI

MCP-in-SoS: Risk assessment framework for open-source MCP servers

This paper addresses the lack of systematic security evaluation for open-source Model Context Protocol (MCP) servers by applying static code analysis to identify Common Weakness Enumeration (CWE) vulnerabilities, mapping them to MITRE CAPEC attack patterns, and introducing a multi-metric risk-assessment framework to guide secure-by-design development.

Pratyay Kumar, Miguel Antonio Guirao Aguilera, Srikathyayani Srikanteswara, Satyajayant Misra, Abu Saleh Md TayeenThu, 12 Ma🤖 cs.AI

Multilingual AI-Driven Password Strength Estimation with Similarity-Based Detection

This research proposes a novel multilingual password strength meter that leverages AI-generated datasets (specifically ChatGPT) and Jaro similarity-based matching to outperform traditional models like PassGAN, demonstrating that incorporating non-English training data significantly enhances detection accuracy for language-specific vulnerabilities, particularly in the Indian context.

Nikitha M. Palaniappan, Ying HeThu, 12 Ma🤖 cs.AI

Paladin: A Policy Framework for Securing Cloud APIs by Combining Application Context with Generative AI

The paper introduces Paladin, a security framework that leverages generative AI to extract semantic meaning from API requests, enabling administrators to easily define and enforce application-aware policies that prevent unrestricted resource consumption, sensitive data access, and broken authentication with high accuracy and reasonable overhead.

Shriti Priya, Julian James Stephen, Arjun NatarajanThu, 12 Ma💻 cs

Post-Quantum Entropy as a Service for Embedded Systems

This paper presents a Quantum Entropy as a Service (QEaaS) system that delivers post-quantum-secured entropy to embedded ESP32 devices, demonstrating that ML-KEM-512 and ML-DSA-44 protocols achieve DTLS 1.3 handshakes significantly faster than classical ECDHE P-256 counterparts while maintaining robust security.

Javier Blanco-Romero, Yuri Melissa Garcia-Niño, Florina Almenares Mendoza, Daniel Díaz-Sánchez, Carlos García-Rubio, Celeste CampoThu, 12 Ma💻 cs

PRoADS: Provably Secure and Robust Audio Diffusion Steganography with latent optimization and backward Euler Inversion

The paper introduces PRoADS, a provably secure and robust audio steganography framework that embeds secret messages into diffusion model noise via orthogonal projection and employs Latent Optimization with Backward Euler Inversion to minimize reconstruction errors, achieving a remarkably low bit error rate of 0.15% under 64 kbps MP3 compression.

YongPeng Yan, Yanan Li, Qiyang Xiao, Yanzhen RenThu, 12 Ma💻 cs

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

This paper proposes a novel multi-layer ensemble defense mechanism combining stacking classifiers, autoencoders, and adversarial training to enhance the robustness of machine learning-based Network Intrusion Detection Systems against adversarial attacks generated by GANs and FGSM, demonstrating improved resilience on the UNSW-NB15 and NSL-KDD datasets.

Nasim Soltani, Shayan Nejadshamsi, Zakaria Abou El Houda, Raphael Khoury, Kelton A. P. Costa, Tiago H. Falk, Anderson R. AvilaThu, 12 Ma🤖 cs.AI

Naïve Exposure of Generative AI Capabilities Undermines Deepfake Detection

This paper demonstrates that the naive exposure of powerful reasoning and image refinement capabilities in commercial generative AI chatbots fundamentally undermines state-of-the-art deepfake detectors by allowing adversaries to use benign, policy-compliant prompts to generate high-quality, identity-preserving images that evade detection, revealing a critical structural mismatch between current threat models and real-world AI capabilities.

Sunpill Kim, Chanwoo Hwang, Minsu Kim, Jae Hong SeoThu, 12 Ma🤖 cs.AI

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

The paper introduces IH-Challenge, a reinforcement learning dataset designed to enhance instruction hierarchy robustness in frontier LLMs, which significantly improves their ability to prioritize instructions against conflicts and adversarial attacks while maintaining helpfulness and minimizing capability regression.

Chuan Guo (Michael Pokorny), Juan Felipe Ceron Uribe (Michael Pokorny), Sicheng Zhu (Michael Pokorny), Christopher A. Choquette-Choo (Michael Pokorny), Steph Lin (Michael Pokorny), Nikhil Kandpal (Michael Pokorny), Milad Nasr (Michael Pokorny), Rai (Michael Pokorny), Sam Toyer, Miles Wang, Yaodong Yu, Alex Beutel, Kai XiaoThu, 12 Ma🤖 cs.AI

Repurposing Backdoors for Good: Ephemeral Intrinsic Proofs for Verifiable Aggregation in Cross-silo Federated Learning

This paper proposes a lightweight, backdoor-based "Intrinsic Proofs" framework that ensures verifiable aggregation in cross-silo federated learning by embedding ephemeral verification signals into model parameters, thereby achieving high detection rates against malicious servers with over 1000x speedup compared to traditional cryptographic methods while preserving client anonymity and final model utility.

Xian Qin, Xue Yang, Xiaohu TangThu, 12 Ma🤖 cs.AI

CacheSolidarity: Preventing Prefix Caching Side Channels in Multi-tenant LLM Serving Systems

CacheSolidarity is a lightweight system that secures multi-tenant LLM serving against Automatic Prefix Caching side-channel attacks by selectively isolating suspicious cache reuse, thereby achieving significantly higher cache efficiency and lower latency compared to existing all-or-nothing isolation defenses.

Panagiotis Georgios Pennas, Konstantinos Papaioannou, Marco Guarnieri, Thaleia Dimitra DoudaliThu, 12 Ma🤖 cs.LG