密码学与安全

Advances in deep learning have enabled the widespread deployment of speaker recognition systems (SRSs), yet they remain vulnerable to score-based impersonation attacks. Existing attacks that operate directly on raw waveforms require a large…

Serverless wallet recovery must balance portability, usability, and privacy. Public registries enable decentralized lookup but naive identifier hashing leaks membership through enumeration. We present VA-DAR, a keyed-discovery protocol for…

Blockchains are diverse in the way they handle communications between their nodes to disseminate information, mitigate attacks, and agree on the next block. While security vulnerabilities have been identified, they rely on an attack…

Recent progress in (Large) Language Models (LMs) has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents have started to be integrated into systems with significant…

A single authentication bypass in a partner SDK grants attackers the identity of every partner in the ecosystem -- and millions of apps use SDKs with exactly this vulnerability. OWASP's 2024 Mobile Top 10 ranks Inadequate Supply Chain…

This paper presents composable attestation as a generalized cryptographic framework for Continuous and Incremental Trust in Distributed Systems,such as Artificial Intelligence (AI) computation, and Open Source Software (OSS) supply chain…

The deployment of Large Reasoning Models (LRMs) in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought (CoT) is manipulated…

Large language models (LLMs) are increasingly being deployed as software engineering agents that autonomously contribute to repositories. A major benefit these agents present is their ability to find and patch security vulnerabilities in…

Large language models (LLMs) increasingly act as autonomous agents, using tools to execute code, read and write files, and access networks, creating novel security risks. To mitigate these risks, agents are commonly deployed and evaluated…

Supervised fine-tuning (SFT) is essential for the development of medical large language models (LLMs), yet prior poisoning studies have mainly focused on the detectable backdoor attacks. We propose a novel poisoning attack targeting the…

We propose a new approach in cryptanalysis based on an evolution of the concept of \textit{Combinatorial Equivalence}. The aim is to rewrite a cryptosystem under a combinatorially equivalent form in order to make appear new properties that…

Network Intrusion Detection Systems (NIDS) have progressively shifted from signature-based techniques toward machine learning and, more recently, deep learning methods. Meanwhile, the widespread adoption of encryption has reduced payload…

Ransomware has become one of the most serious cybersecurity threats causing major financial losses and operational disruptions worldwide.Traditional detection methods such as static analysis, heuristic scanning and behavioral analysis often…

Large multimodal model powered GUI agents are emerging as high-privilege operators on mobile platforms, entrusted with perceiving screen content and injecting inputs. However, their design operates under the implicit assumption of Visual…

To preserve data privacy, multi-party computation (MPC) enables executing Machine Learning (ML) algorithms on private data. However, MPC frameworks do not include optimized operations on sparse data. This absence makes them unsuitable for…

The ubiquity of closed-weight language models with public-facing APIs has generated interest in forensic methods, both for extracting hidden model details (e.g., parameters) and for identifying models by their outputs. One successful…

The prospective emergence of large-scale quantum computers capable of executing Shor's algorithm at cryptographically relevant scale would render widely deployed public-key cryptography computationally insecure. Under this threat model,…

The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and…

Watermarking has emerged as a leading technical proposal for attributing generative AI content and is increasingly cited in global governance frameworks. This position paper argues that current implementations risk serving as symbolic…

The growing adoption of Large Language Models (LLMs) has influenced the development of Small Language Models (SLMs) for on-device deployment across smartphones and edge devices, offering enhanced privacy, reduced latency, server-free…