密码学与安全

Large Language Models (LLMs) have emerged as powerful tools for automating programming tasks, including security-related ones. However, they can also introduce vulnerabilities during code generation, fail to detect existing vulnerabilities,…

Modern confidential computing executes sensitive computation in an abstraction called confidential VMs and protects from the hypervisor, host OS, and other co-resident VMs. It has been shown that an attacker can inject malicious interrupts…

Greybox fuzzing has achieved success in revealing bugs and vulnerabilities in programs. However, randomized mutation strategies have limited the fuzzer's performance on structured data. Specialized fuzzers can handle complex structured…

Artificial intelligence (AI) systems are increasingly adopted as tool-using agents that can plan, observe their environment, and take actions over extended time periods. This evolution challenges current evaluation practices where the AI…

With the rapid development of LLM-based multi-agent systems (MAS), their significant safety and security concerns have emerged, which introduce novel risks going beyond single agents or LLMs. Despite attempts to address these issues, the…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically…

Mobile core networks rely on several signalling protocols in parallel, such as SS7, Diameter, and GTP, so many security-relevant problems become visible only when their interactions are analyzed jointly. At the same time, labeled examples…

An SRAM Physical Unclonable Function (PUF) can distinguish SRAM modules by analyzing the inherent randomness of their start-up behavior. However, the effectiveness of this technique varies depending on the design and fabrication of the SRAM…

In cloud-based endpoint auditing, security administrators often rely on the cloud to perform causality analysis over log-derived versioned provenance graphs to investigate suspicious attack behaviors. However, the cloud may be distrusted or…

We present a fine-tuned RoBERTa-base classifier (125M parameters) for mapping Common Vulnerabilities and Exposures (CVE) descriptions to Common Weakness Enumeration (CWE) categories. We construct a large-scale training dataset of 234,770…

Generative AI deployment poses unprecedented challenges to content safety and privacy. However, existing defense mechanisms are often tailored to specific architectures (e.g., Diffusion Models or GANs), creating fragile "defense silos" that…

Automated LLM vulnerability scanners are increasingly used to assess security risks by measuring different attack type success rates (ASR). Yet the validity of these measurements hinges on an often-overlooked component: the evaluator who…

As database deployments shift toward cloud platforms and edge devices, thin clients need to securely retrieve sensitive records without leaking their query intent or metadata to the proxies that mediate access. Oblivious Transfer (OT) is a…

Electronic banking portals often sit in front of enterprise resource planning (ERP) systems such as SAP, mediating payment requests between users and back end financial infrastructure. When these integrations place excessive trust in client…

Over the years, access control systems have become increasingly more complex, often causing a disconnect between what is envisaged by the stakeholders in decision-making positions and the actual permissions granted as evidenced from access…

Hosted large language models are increasingly accessed through remote APIs, but the API boundary still offers little direct evidence that a returned output actually corresponds to the client-visible request. Recent audits of shadow APIs…

Most jailbreak techniques for Large Language Models (LLMs) primarily rely on prompt modifications, including paraphrasing, obfuscation, or conversational strategies. Meanwhile, abliteration techniques (also known as targeted ablations of…

Deep learning-based perception pipelines in autonomous ground vehicles are vulnerable to both adversarial manipulation and network-layer disruption. We present a systematic, on-hardware experimental evaluation of five attack classes: FGSM,…

Honeypots are deception systems that emulate vulnerable services to collect threat intelligence. While deploying many honeypots increases the opportunity to observe attacker behaviour, in practise network and computational resources limit…

We study several problems in differentially private domain discovery, where each user holds a subset of items from a shared but unknown domain, and the goal is to output an informative subset of items. For set union, we show that the simple…