密码学与安全

Fully Homomorphic Encryption (FHE) enables computations directly on encrypted data, but its high computational cost remains a significant barrier. Writing efficient FHE code is a complex task requiring cryptographic expertise, and finding…

UAVs have the potential to revolutionize urban management and provide valuable services to citizens. They can be deployed across diverse applications, including traffic monitoring, disaster response, environmental monitoring, and numerous…

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes…

Sponge attacks increasingly threaten LLM systems by inducing excessive computation and DoS. Existing defenses either rely on statistical filters that fail on semantically meaningful attacks or use static LLM-based detectors that struggle to…

Secure code review is critical at the pre-commit stage, where vulnerabilities must be caught early under tight latency and limited-context constraints. Existing SAST-based checks are noisy and often miss immature, context-dependent…

Amazon published its Frontier Model Safety Framework (FMSF) as part of the Paris AI summit, following which we presented a report on Amazon's Premier model. In this report, we present an evaluation of Nova 2.0 Lite. Nova 2.0 Lite was made…

Memory corruption attacks have been prevalent in software for a long time. Some mitigation strategies against these attacks do exist, but they are not as far-reaching or as efficient as the CHERI architecture. CHERI uses capabilities to…

Prompt-based attack techniques are one of the primary challenges in securely deploying and protecting LLM-based AI systems. LLM inputs are an unbounded, unstructured space. Consequently, effectively defending against these attacks requires…

Aggregate analytics over conversational data are increasingly used for safety monitoring, governance, and product analysis in large language model systems. A common practice is to embed conversations, cluster them, and publish short textual…

For the past three decades, the architecture of the internet has rested on two primary pillars - communication on the World Wide Web and Value such as Bitcoin/Distributed ledgers. However, a third critical pillar, Private Coordination has…

The Python Package Index (PyPI) has become a target for malicious actors, yet existing detection tools generate false positive rates of 15-30%, incorrectly flagging one-third of legitimate packages as malicious. This problem arises because…

The increasing cyber threats to critical infrastructure highlight the importance of private companies and government agencies in detecting and sharing information about threat activities. Although the need for improved threat information…

Large web-scale datasets have driven the rapid advancement of pre-trained language models (PLMs), but unauthorized data usage has raised serious copyright concerns. Existing dataset ownership verification (DOV) methods typically assume that…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential, yet they face two major challenges: generalization and…

Federated Prompt Learning has emerged as a communication-efficient and privacy-preserving paradigm for adapting large vision-language models like CLIP across decentralized clients. However, the security implications of this setup remain…

The rapid adoption of machine learning (ML) technologies has driven organizations across diverse sectors to seek efficient and reliable methods to accelerate model development-to-deployment. Machine Learning Operations (MLOps) has emerged…

Recent advances in operating system (OS) agents have enabled vision-language models (VLMs) to directly control a user's computer. Unlike conventional VLMs that passively output text, OS agents autonomously perform computer-based tasks in…

Latent Diffusion Models (LDMs) have established themselves as powerful tools in the rapidly evolving field of image generation, capable of producing highly realistic images. However, their widespread adoption raises critical concerns about…

Several companies have deployed watermark-based detection to identify AI-generated content. However, attribution--the ability to trace back to the user of a generative AI (GenAI) service who created a given AI-generated content--remains…

The proliferation of the Internet of Things (IoT) has introduced a massive influx of devices into the market, bringing with them significant security vulnerabilities. In this diverse ecosystem, robust IoT device identification is a critical…