密码学与安全

As Field-Programmable Gate Arrays (FPGAs) scale in multi-tenant cloud and edge-AI environments, the configuration bitstream has become a critical, yet opaque, security boundary. Existing hardware Trojan detection methods often rely on…

Autonomous AI agents are increasingly deployed on blockchain platforms, yet the design space that governs their interaction remains poorly understood. This convergence, where autonomous agents operate on and within decentralized systems, is…

The new wave of adversarial attacks that utilize gradient-related vulnerabilities in neural network-based classifiers makes Network Intrusion Detection Systems more open to such threats. Although state-of-the-art adversarial training…

Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representation shifts associated with jailbreak success, but they leave a more fundamental question…

Automated intrusion-style workflows require LLM agents to reason over partial observations, tool outputs, and executable artifacts under bounded budgets. A single LLM instance often compresses evidence extraction, planning, execution, and…

Modern cryptography is hinged on "not learning from mistakes": trying numerous wrong keys, should not help one identify the right key. Indeed, it worked -- until recently when the surprising power of AI to see pattern in apparent randomness…

Embedded and Internet-of-Things (IoT) devices play a critical role in modern life. Their software and firmware, often developed in memory-unsafe languages like C, are susceptible to memory safety vulnerabilities that can lead to…

This position paper argues that computer science conferences should require tamper-evident, nonrepudiable attestations of experimental results. We name the underlying problem experiment nonrepudiation: a compliant protocol must bind the…

Since the official release of ChatGPT in 2022, large language models (LLMs) have rapidly evolved from chatbot-style interfaces into agentic systems that can delegate work through tools and newly spawned subagents. While these capabilities…

The realtime analysis and secure transmission of electrocardiogram ECG signals are critical for accurate diagnosis and safeguarding patient privacy in telemedicine applications This study presents a novel realtime ECG monitoring system that…

Security Level 5 (SL5) is a security posture for AI systems that could plausibly thwart top-priority operations by the world's most cyber-capable institutions: those with extensive resources, state-level infrastructure, and expertise years…

Federated Learning (FL) with parameter-efficient fine-tuning, such as Low-Rank Adaptation (LoRA), enables scalable model training on distributed data. However, when combined with Differential Privacy (DP), LoRA often introduces errors…

Persistent memory attacks against LLM agents achieve high attack success rates against open-source models. In these attacks, malicious instructions injected via RAG-retrieved documents are stored in persistent memory and executed in later…

While contemporary deep learning malware detectors define a dominant defense paradigm, their sophistication also exposes them to novel structural evasion attacks, a limitation we attribute to their inherent inability to express epistemic…

LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to write secure…

Kettle is an attested build system that produces cryptographically verifiable provenance for software built inside Trusted Execution Environments (TEEs). A Kettle build records the source commit, dependency set, toolchain, build…

Large language models (LLMs) rely on deterministic pseudorandom number generators (PRNGs) for autoregressive sampling, creating a critical supply-chain attack surface overlooked by existing defenses. We present SeedHijack, a backdoor attack…

Browser agents are increasingly deployed in long-horizon tasks, which require executing extended action chains to accomplish user goals. However, this prolonged execution process provides attackers with more opportunities to inject…

Many-shot jailbreaking (MSJ) causes safety-aligned language models to answer harmful queries by preceding them with many harmful question-answer demonstrations. We study why this attack becomes stronger as the number of demonstrations…

Motivated by the challenge to improve the adversarial robustness, security, and trust of medical decision making intelligent agents, this study develops a full-link security enhancement framework, which describes "input risk perception -…