Related papers: STACK: Adversarial Attacks on LLM Safeguard Pipeli…

Meltdown and Spectre exploit microarchitectural changes the CPU makes during transient out-of-order execution. Using side-channel techniques, these attacks enable leaking arbitrary data from memory. As state-of-the-art software mitigations…

Misconfiguration, excessive privilege, and fragmented controls remain major causes of cloud-infrastructure incidents. This paper proposes an open-source framework that contributes a cross-platform identity-resource graph for Kubernetes and…

As large language models (LLMs) are increasingly deployed in diverse applications, including chatbot assistants and code generation, aligning their behavior with safety and ethical standards has become paramount. However, jailbreak attacks,…

DRAM chips are vulnerable to read disturbance phenomena (e.g., RowHammer and RowPress), where repeatedly accessing or keeping open a DRAM row causes bitflips in nearby rows. Attackers leverage RowHammer bitflips in real systems to take over…

Large Language Models (LLMs) have transformed human-machine interaction since ChatGPT's 2022 debut, with Retrieval-Augmented Generation (RAG) emerging as a key framework that enhances LLM outputs by integrating external knowledge. However,…

Large language models (LLMs) increasingly act as autonomous agents, using tools to execute code, read and write files, and access networks, creating novel security risks. To mitigate these risks, agents are commonly deployed and evaluated…

Securing neural networks (NNs) against model extraction and parameter exfiltration attacks is an important problem primarily because modern NNs take a lot of time and resources to build and train. We observe that there are no…

Fine-tuning is an essential process to improve the performance of Large Language Models (LLMs) in specific domains, with Parameter-Efficient Fine-Tuning (PEFT) gaining popularity due to its capacity to reduce computational demands through…

As large language models (LLMs) move from research prototypes to enterprise systems, their security vulnerabilities pose serious risks to data privacy and system integrity. This study benchmarks various Llama model variants against the…

The Internet of Things (IoT) ecosystem allows communication between billions of devices worldwide that are collecting data autonomously. The vast amount of data generated by these devices must be controlled totally securely. The centralized…

This work addresses challenges related to attacks on social tagging systems, which often comes in a form of malicious annotations or profile injection attacks. In particular, we study various countermeasures against two types of threats for…

The power consumption of a microprocessor is a huge channel for information leakage. While the most popular exploitation of this channel is to recover cryptographic keys from embedded devices, other applications such as mobile app…

Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic…

Timing-based side and covert channels in processor caches continue to be a threat to modern computers. This work shows for the first time a systematic, large-scale analysis of Arm devices and the detailed results of attacks the processors…

Small and medium sized businesses (SMBs) face an escalating cybersecurity threat landscape, yet most lack the resources to staff full Security Operations Centers (SOCs) or deploy enterprise grade detection platforms. This paper presents…

The outsourcing of the design and manufacturing of integrated circuits (ICs) in the current horizontal semiconductor integration flow has posed various security threats due to the presence of untrusted entities, such as overproduction of…

Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations…

Large language models remain vulnerable to jailbreak attacks, and single-layer defenses often trade security for usability. We present TRYLOCK, the first defense-in-depth architecture that combines four heterogeneous mechanisms across the…

Large Language Models (LLMs) are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that…

LLM agents are highly vulnerable to Indirect Prompt Injection (IPI), where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defenses treat IPI as an input-level semantic discrimination…