Related papers: BliMe Linter
Trusted Platform Modules constitute an integral building block of modern security features. Moreover, as Windows 11 made a TPM 2.0 mandatory, they are subject to an ever-increasing academic challenge. While discrete TPMs - as found in…
Hardware-assisted memory protection features are increasingly being deployed in COTS processors. ARMv8.5 Memory Tagging Extensions (MTE) is a recent example, which has been used to provide probabilistic checks for memory safety. This use of…
The exploitation of certification tools by end users represents a fundamental aspect of the development of quantum technologies as the hardware scales up beyond the regime of classical simulatability. Certifying quantum networks becomes…
The rapid advancement and widespread use of large language models (LLMs) have raised significant concerns regarding the potential leakage of personally identifiable information (PII). These models are often trained on vast quantities of…
Fog computing, a non-trivial extension of cloud computing to the edge of the network, has great advantage in providing services with a lower latency. In smart grid, the application of fog computing can greatly facilitate the collection of…
The cold-start issue is the challenge when we talk about recommender systems, especially in the case when we do not have the past interaction data of new users or new items. Content-based features or hybrid solutions are common as…
The current landscape of system-on-chips (SoCs) security verification faces challenges due to manual, labor-intensive, and inflexible methodologies. These issues limit the scalability and effectiveness of security protocols, making bug…
As a result of decades of research, Windows malware detection is approached through a plethora of techniques. However, there is an ongoing mismatch between academia -- which pursues an optimal performances in terms of detection rate and low…
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks. However, these models often infer and reveal sensitive biometric attributes such as race, gender, age, body weight, and eye color;…
Large Language Models (LLMs) have become integral to numerous domains, significantly advancing applications in data management, mining, and analysis. Their profound capabilities in processing and interpreting complex language data, however,…
Machine learning (ML) models are known to be vulnerable to a number of attacks that target the integrity of their predictions or the privacy of their training data. To carry out these attacks, a black-box adversary must typically possess…
LLM inference and serving systems have become security-critical infrastructure; however, many of their most concerning failures arise from the serving layer rather than from model behavior alone. Modern inference engines combine KV cache,…
Bulk-bitwise processing-in-memory (PIM), where large bitwise operations are performed in parallel by the memory array itself, is an emerging form of computation with the potential to mitigate the memory wall problem. This paper examines the…
Non-volatile random access memory (NVRAM) offers byte-addressable persistence at speeds comparable to DRAM. However, with caches remaining volatile, automatic cache evictions can reorder updates to memory, potentially leaving persistent…
In this paper we present LiM ("Less is More"), a malware classification framework that leverages Federated Learning to detect and classify malicious apps in a privacy-respecting manner. Information about newly installed apps is kept locally…
The ever-increasing size of open-source Large Language Models (LLMs) renders local deployment impractical for individual users. Decentralized computing has emerged as a cost-effective solution, allowing individuals and small companies to…
Large language model (LLM) applications are blindfolded to the infrastructure underneath and generate tokens autoregressively, indifferent to the system load, thus risking inferencing latency inflation and poor user experience. Our…
The deployment of large language models (LLMs) on third-party devices requires new ways to protect model intellectual property. While Trusted Execution Environments (TEEs) offer a promising solution, their performance limits can lead to a…
As the Ethereum platform continues to mature and gain widespread usage, it is crucial to maintain high standards of smart contract writing practices. While bad practices in smart contracts may not directly lead to security issues, they…
Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…