密码学与安全

Diffusion models depend on pseudo-random number generators (PRNGs) for latent noise sampling. We present DiffusionHijack, a supply-chain backdoor attack that hijacks the PRNG to deterministically control generated images. A malicious PRNG,…

Security often receives insufficient developer attention because it does not directly generate visible value, leading to underinvestment in practice. We evaluate a countermeasure by team-level incentives tied to measurable security…

LLM-powered agents can silently delete documents, leak credentials, or transfer funds on a routine user request, not because the agent was attacked, but because the skill it invoked broke its own declared safety rules. We call these…

In the official whitepaper of Secure Encrypted Virtualization with Secure Nested Paging (SEV-SNP), AMD explicitly emphasizes the capability to prevent Trusted Computing Base (TCB) rollback attacks. Cryptographically, this is realized by…

Modern cloud-native environments present a fundamentally different exfiltration threat surface than traditional file-based scenarios. Attackers targeting AWS, GCP, Azure, and OCI steal S3 presigned URLs, container images, Kubernetes…

Standalone virtual reality (VR) headsets process highly sensitive personal, professional, and health-related data, yet their susceptibility to non-contact physical side channels remains largely unexplored. Existing side-channel attacks…

Programmatic skills in LLM ecosystems consist of a natural-language description and executable implementation files. Users and LLMs rely on the description to understand the skill's scope. However, the implementation may perform…

Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary…

Homomorphic encryption (HE) enables computation over encrypted data, offering strong privacy guarantees for untrusted computing environments. Practical adoption remains limited by high computational complexity, large ciphertext sizes, and…

Monitoring the chain-of-thought (CoT) of reasoning models is a promising approach for detecting covert misbehavior (i.e., hidden objectives) in code generation tasks. While large models (GPT-5, Gemini-3-Flash) can serve as effective CoT…

Existing physical adversarial attacks on vision-based autonomous driving induce time-evolving perception errors, including biased object tracking or trajectory prediction, through (i) sophisticated physical patch inducing detection box…

Existing automated red-teaming pipelines often miss attacks that depend on attacker identity, framing, or multi-turn tactics. This under-coverage underestimates real-world risk. We introduce Persona-Conditioned Adversarial Prompting (PCAP),…

Script-language runtimes such as Python, Lua, and JavaScript are widely deployed in security sensitive contexts, yet they remain difficult to test because valid inputs must satisfy syntax, dynamic type constraints, and object-level…

In recent trends, one can observe Large Language Models (LLMs) are exposed to backdoor attacks where vicious triggers added during training or model editing to elicit harmful outputs on specific input patterns while maintaining clean…

Organizations increasingly depend on endpoint devices and corporate communication channels, yet they still face critical risks such as sensitive data leakage, suspicious user behavior, and the circulation of hateful or harmful language in…

Online fraud in Africa has reached an epidemic scale. The few cybersecurity tools that exist are out of reach for ordinary citizens, built almost exclusively for SOC analysts and technically literate users sitting on stable broadband. That…

AI chatbots are becoming a primary interface for seeking information. As their popularity grows, chatbot providers are starting to deploy advertising and analytics. Despite this, tracking on AI chatbots has not been systematically studied.…

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…

Many large language models (LLMs) use reasoning to generate responses but do not reveal their full reasoning traces (a.k.a. chains of thought), instead outputting only final answers and brief reasoning summaries. To demonstrate that hiding…

Gradient boosted decision trees, particularly XGBoost, are among the most effective methods for tabular data. As deployment in sensitive settings increases, cryptographic guarantees of model integrity become essential. We present ZKBoost,…