密码学与安全

Mixture-of-Experts (MoE) offers flexible graph reasoning by combining multiple views of a graph through a learned router. We investigate routing-aware explanations for MoE graph models in malware detection using control flow graphs (CFGs).…

Large Language Models (LLMs) & Generative AI are transforming cybersecurity, enabling both advanced defenses and new attacks. Organizations now use LLMs for threat detection, code review, and DevSecOps automation, while adversaries leverage…

Privacy preserving machine learning deployments in sensitive deep learning applications; from medical imaging to autonomous systems; increasingly require combining multiple techniques. Yet, practitioners lack systematic guidance to assess…

Defending LLMs against adversarial jailbreak attacks remains an open challenge. Existing defenses rely on binary classifiers that fail when adversarial input falls outside the learned decision boundary, and repeated fine-tuning is…

Private convolutional neural network (CNN) inference based on secure two-party computation (2PC) suffers from high communication and latency overhead, especially from convolution layers. In this paper, we propose UFO, a quantized 2PC…

We provide background on emerging challenges and future directions with media integrity and authentication methods, focusing on distinguishing AI-generated media from authentic content captured by cameras and microphones. We evaluate…

Ransomware has yet to reach orbit, but the conditions for such an attack already exist. This paper presents the first game-theoretic framework for modeling ransomware against satellites: the orbital escalation game. In this model, the…

The Internet of Things (IoT) presents a unique cybersecurity challenge due to its vast network of interconnected, resource-constrained devices. These vulnerabilities not only threaten data integrity but also the overall functionality of IoT…

Digital identity verification often forces a privacy trade-off, where users must disclose sensitive personal data to prove simple eligibility criteria. As blockchain applications integrate with regulated environments, this over-disclosure…

As Large Language Models (LLMs) are increasingly integrated into automated decision-making pipelines, specifically within Human Resources (HR), the security implications of Indirect Prompt Injection (IPI) become critical. While a prevailing…

Personalized federated learning (PFL) creates client-specific models to handle data heterogeneity. Previously, PFL has been shown to be naturally resistant to backdoor attack propagation across clients. In this work, we reveal that PFL…

Prompt injection attacks insert malicious instructions into an LLM's input to steer it toward an attacker-chosen task instead of the intended one. Existing detection defenses typically classify any input with instruction as malicious,…

Binary Function Similarity (BFS), the problem of determining whether two binary functions originate from the same source code, has been extensively studied in recent research across security, software engineering, and machine learning…

Decentralized Finance (DeFi) has turned blockchains into financial infrastructure, allowing anyone to trade, lend, and build protocols without intermediaries, but this openness exposes pools of value controlled by code. Within five years,…

The advent of quantum computing threatens classical cryptographic mechanisms, demanding new strategies for securing communication networks. Since real-world networks cannot be fully Quantum Key Distribution (QKD)-enabled due to…

File encrypting ransomware increasingly employs intermittent encryption techniques, encrypting only parts of files to evade classical detection methods. These strategies, exemplified by ransomware families like BlackCat, complicate file…

The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a…

As on-device LLMs(e.g., Apple on-device Intelligence) are widely adopted to reduce network dependency, improve privacy, and enhance responsiveness, verifying the legitimacy of models running on local devices becomes critical. Existing…

In this paper we introduce a rank $2$ lattice over a polynomial ring arising from the public key of the BIKE cryptosystem. The secret key is a sparse vector in this lattice. We study properties of this lattice and generalize the recovery of…

This paper introduces {\em truncated inner $c$-differential cryptanalysis}, a technique that enables the practical application of $c$-differential uniformity to block ciphers. While Ellingsen et al. (IEEE Trans. Inf. Theory, 2020)…