Related papers: Beyond Over-Protection: A Targeted Approach to Spe…

Foundation models are now increasingly being developed for Earth observation (EO), yet they often rely on stochastic masking that do not explicitly enforce physics constraints; a critical trustworthiness limitation, in particular for…

Confidential computing on GPUs, like NVIDIA H100, mitigates the security risks of outsourced Large Language Models (LLMs) by implementing strong isolation and data encryption. Nonetheless, this encryption incurs a significant performance…

Running LLMs on end devices has garnered significant attention recently due to their advantages in privacy preservation. With the advent of lightweight LLM models and specially designed GPUs, on-device LLM inference has achieved the…

The widespread adoption of open-source software (OSS) has accelerated software innovation but also increased security risks due to the rapid propagation of vulnerabilities and silent patch releases. In recent years, large language models…

Autoregressive decoding inherently limits the inference throughput of Large Language Model (LLM) due to its sequential dependency. Speculative decoding mitigates this by verifying multiple predicted tokens in parallel, but its efficiency…

A recent discovery of a new class of microarchitectural attacks called Spectre picked up the attention of the security community as these attacks can circumvent many traditional mechanisms of defense. One of the attacks---Bounds Check…

Vision-Language Models (VLMs) enable powerful multimodal reasoning but suffer from slow autoregressive inference, limiting their deployment in real-time applications. We introduce Spec-LLaVA, a system that applies speculative decoding to…

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…

Increasing system-on-chip (SoC) heterogeneity, deep hardware/software integration, and the proliferation of third-party intellectual property (IP) have brought security validation to the forefront of semiconductor design. While simulation…

Large Vision-Language Models (LVLMs) can be vulnerable to adversarial images that subtly bias their outputs toward plausible yet incorrect responses. We introduce a general, efficient, and training-free defense that combines image…

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…

Static analysis, the process of examining code without executing it, is crucial for identifying software issues. Yet, static analysis is hampered by its complexity and the need for customization for different targets. Traditional static…

Transient Execution Attacks (TEAs) have gradually become a major security threat to modern high-performance processors. They exploit the vulnerability of speculative execution to illegally access private data, and transmit them through…

Vision-Language Models (VLMs) have gained considerable prominence in recent years due to their remarkable capability to effectively integrate and process both textual and visual information. This integration has significantly enhanced…

Large Language Models (LLMs) have shown remarkable capabilities in solving various programming tasks, such as code generation. However, their potential for code optimization, particularly in performance enhancement, remains largely…

Scam detection remains a critical challenge in cybersecurity as adversaries craft messages that evade automated filters. We propose a Hierarchical Scam Detection System (HSDS) that combines a lightweight multi-model voting front end with a…

Software vulnerabilities continue to be ubiquitous, even in the era of AI-powered code assistants, advanced static analysis tools, and the adoption of extensive testing frameworks. It has become apparent that we must not simply prevent…

Deep learning-based approaches, particularly those leveraging pre-trained language models (PLMs), have shown promise in automated software vulnerability detection. However, existing methods are predominantly limited to specific programming…

Transient execution attacks, also called speculative execution attacks, have drawn much interest as they exploit the transient execution of instructions, e.g., during branch prediction, to leak data. Transient execution is fundamental to…

In this paper, we analyze the security of programming languages and their execution environments (compilers and interpreters) with respect to Spectre attacks. The analysis shows that only 16 out of 42 execution environments have mitigations…