密码学与安全
The AI Control research agenda aims to develop control protocols: safety techniques that prevent untrusted AI systems from taking harmful actions during deployment. Because human oversight is expensive, one approach is trusted monitoring,…
Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream black-box jailbreak attacks on VLMs work by distributing…
The advent of quantum computation compels the cryptographic community to design digital signature schemes whose security extends beyond the classical hardness assumptions. In this work, we introduce Spinel, a post-quantum digital signature…
Phishing attacks represents one of the primary attack methods which is used by cyber attackers. In many cases, attackers use deceptive emails along with malicious attachments to trick users into giving away sensitive information or…
AI coding assistants produce vulnerable code in 45\% of security-relevant scenarios~\cite{veracode2025}, yet no public training dataset teaches both traditional web security and AI/ML-specific defenses in a format suitable for instruction…
Service Level Agreement (SLA) monitoring in service-oriented environments suffers from inherent trust conflicts when providers self-report metrics, creating incentives to underreport violations. We introduce a framework for generating…
We propose a system for marking sensitive or copyrighted texts to detect their use in fine-tuning large language models under black-box access with statistical guarantees. Our method builds digital ``marks'' using invisible Unicode…
Since many applications and services require pseudorandom numbers (PRNs), it is feasible to generate specific PRNs under given key values and input messages using Key Derivation Functions (KDFs). These KDFs are primarily constructed based…
Securing software supply chains is a growing challenge due to the inadequacy of existing datasets in capturing the complexity of next-gen attacks, such as multiphase malware execution, remote access activation, and dynamic payload…
Blockchain and distributed ledger technologies (DLTs) facilitate decentralized computations across trust boundaries. However, ensuring complex computations with low gas fees and confidentiality remains challenging. Recent advances in…
The ever-increasing security vulnerabilities in the Internet-of-Things (IoT) systems require improved threat detection approaches. This paper presents a compact and efficient approach to detect botnet attacks by employing an integrated…
The success of AI is based on the availability of data to train models. While in some cases a single data custodian may have sufficient data to enable AI, often multiple custodians need to collaborate to reach a cumulative size required for…
Penetration-testing is crucial for identifying system vulnerabilities, with privilege-escalation being a critical subtask to gain elevated access to protected resources. Language Models (LLMs) presents new avenues for automating these…
Detecting personally identifiable information (PII) in user queries is critical for ensuring privacy in question-answering systems. Current approaches mainly redact all PII, disregarding the fact that some of them may be contextually…
Current agentic AI architectures are fundamentally incompatible with the security and epistemological requirements of high-stakes scientific workflows. The problem is not inadequate alignment or insufficient guardrails, it is architectural:…
The Cybersecurity Maturity Model Certification (CMMC) framework provides a common standard for protecting sensitive unclassified information in defense contracting. While CMMC defines assessment objectives and control requirements, limited…
Unlike Ethereum, which was conceived as a general-purpose smart-contract platform, Bitcoin was designed primarily as a transaction ledger for its native currency, which limits programmability for conditional applications. This constraint is…
Static Application Security Testing (SAST) tools are integral to modern DevSecOps pipelines, yet tools like CodeQL, Semgrep, and SonarQube remain fundamentally constrained: they require expert-crafted queries, generate excessive false…
Large Language Models (LLMs) deploy safety mechanisms to prevent harmful outputs, yet these defenses remain vulnerable to adversarial prompts. While existing research demonstrates that jailbreak attacks succeed, it does not explain…
Differential Privacy (DP) considers a scenario in which an adversary has almost complete information about the entries of a database. This worst-case assumption is likely to overestimate the privacy threat faced by an individual in…