密码学与安全

The rapid proliferation of agentic AI skill ecosystems -- exemplified by OpenClaw (228,000 GitHub stars) and Anthropic Agent Skills (75,600 stars) -- has introduced a critical supply chain attack surface. The ClawHavoc campaign…

Financial systems run nonstop and must stay reliable even during cyber incidents. Modern attacks move across many services (apps, APIs, identity, payment rails), so defenders must make a sequence of actions under time pressure. Most…

Intrusion detection in IoT and industrial networks requires models that can detect rare attacks at low false-positive rates while remaining reliable under evolving traffic and limited labels. Existing IDS solutions often report strong…

Retrieval-augmented generation (RAG) has emerged as a powerful paradigm for enhancing multimodal large language models by grounding their responses in external, factual knowledge and thus mitigating hallucinations. However, the integration…

We introduce Reverse CAPTCHA, an evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in otherwise normal-looking text. Unlike traditional CAPTCHAs that distinguish humans from…

Domain fine-tuning is a common path to deploy small instruction-tuned language models as customer-support assistants, yet its effects on safety-aligned behavior and privacy are not well understood. In real deployments, such assistants…

The learning parity with noise (LPN) problem is a well-established computational challenge whose difficulty is critical to the security of several post-quantum cryptographic primitives such as HQC and Classic McEliece. Classically, the…

Image-generative models are widely deployed across industries. Recent studies show that they can be exploited to produce policy-violating content. Existing mitigation strategies primarily operate at the pre- or mid-generation stages through…

The prevalence of malicious packages in open-source repositories, such as PyPI, poses a critical threat to the software supply chain. While Large Language Models (LLMs) have emerged as a promising tool for automated security tasks, their…

Database-driven cognitive radio networks (DB-CRNs) enable dynamic spectrum sharing through geolocation databases but introduce critical security and privacy challenges, including mandatory location disclosure, susceptibility to location…

GPU memory errors are a critical threat to deep learning (DL) frameworks, leading to crashes or even security issues. We introduce GPU-Fuzz, a fuzzer locating these issues efficiently by modeling operator parameters as formal constraints.…

The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI Trojans. These AI trojans are malicious, hidden backdoors…

Federated Learning (FL) enables collaborative, privacy-preserving model training, but supporting the "Right to be Forgotten" is especially challenging because data influences the model through distributed and interleaved client updates.…

A Covert Channel (CC) exploits legitimate communication mechanisms to stealthily transmit information, often bypassing traditional security controls. Among these, a novel paradigm called History Covert Channels (HCC) leverages past network…

Neural networks increasingly run on hardware outside the user's control (cloud GPUs, inference marketplaces). Yet ML-as-a-Service reveals little about what actually ran or whether returned outputs faithfully reflect the intended inputs.…

The Synthetic Minority Over-sampling Technique (SMOTE) is one of the most widely used methods for addressing class imbalance and generating synthetic data. Despite its popularity, little attention has been paid to its privacy implications;…

Consumer electronics (CE) connected to the Internet of Things are susceptible to various attacks, including DDoS and web-based threats, which can compromise their functionality and facilitate remote hijacking. These vulnerabilities allow…

We analyze answers generated by generative engines (GEs) from the perspectives of citation publishers and the content-injection barrier, defined as the difficulty for attackers to manipulate answers to user prompts by placing malicious…

Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined target responses. However, restricting the objective as inducing fixed targets…

Leaderboards for LRMs have turned evaluation into a competition, incentivizing developers to optimize directly on benchmark suites. A shortcut to achieving higher rankings is to incorporate evaluation benchmarks into the training data,…