Related papers: AMuLeT: Automated Design-Time Testing of Secure Sp…

Recently discovered Spectre and meltdown attacks affects almost all processors by leaking confidential information to other processes through side-channel attacks. These vulnerabilities expose design flaws in the architecture of modern…

Security vulnerability analysis of Integrated Circuits using conventional design-time validation and verification techniques (like simulations, emulations, etc.) is generally a computationally intensive task and incomplete by nature,…

Recent advancements in speculative decoding have demonstrated considerable speedup across a wide array of large language model (LLM) tasks. Speculative decoding inherently relies on sacrificing extra memory allocations to generate several…

Spectre attacks and their many subsequent variants are a new vulnerability class affecting modern CPUs. The attacks rely on the ability to misguide speculative execution, generally by exploiting the branch prediction structures, to execute…

Modern out-of-order processors face speculative execution attacks. Despite various proposed software and hardware mitigations to prevent such attacks, new attacks keep arising from unknown vulnerabilities. Thus, a formal and rigorous…

Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as…

Large Language Models (LLMs) have exhibited great performance in autonomously calling various tools in external environments, leading to better problem solving and task automation capabilities. However, these external tools also amplify…

Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. However, the cascaded perception, reasoning, and tool-calling…

Machine learning (ML) models are susceptible to various risks to security, privacy, and fairness. Most defenses are designed to protect against each risk individually (intended interactions) but can inadvertently affect susceptibility to…

Speculative vulnerabilities such as Spectre and Meltdown expose speculative execution state that can be exploited to leak information across security domains via side-channels. Such vulnerabilities often stay undetected for a long time as…

On-device machine learning (ML) introduces new security concerns about model privacy. Storing valuable trained ML models on user devices exposes them to potential extraction by adversaries. The current mainstream solution for on-device…

Application designers have moved to integrate large language models (LLMs) into their products. However, many LLM-integrated applications are vulnerable to prompt injections. While attempts have been made to address this problem by building…

CPUs provide isolation mechanisms like virtualization and privilege levels to protect software. Yet these focus on architectural isolation while typically overlooking microarchitectural side channels, exemplified by Meltdown and Foreshadow.…

SPEculative Execution side Channel Hardware (SPEECH) Vulnerabilities have enabled the notorious Meltdown, Spectre, and L1 terminal fault (L1TF) attacks. While a number of studies have reported different variants of SPEECH vulnerabilities,…

Speculative execution enhances processor performance by predicting intermediate results and executing instructions based on these predictions. However, incorrect predictions can lead to security vulnerabilities, as speculative instructions…

With ChatGPT as a representative, tons of companies have began to provide services based on large Transformers models. However, using such a service inevitably leak users' prompts to the model provider. Previous studies have studied secure…

Behavioral model diagrams, e.g., sequence diagrams, are an essential form of documentation that are typically designed by system engineers from requirements documentation, either fully manually or assisted by design tools. With the growing…

Cryptographic research takes software timing side channels seriously. Approaches to mitigate them include constant-time coding and techniques to enforce such practices. However, recent attacks like Meltdown [42], Spectre [37], and…

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

Early exiting has recently emerged as a promising technique for accelerating large language models (LLMs) by effectively reducing the hardware computation and memory access. In this paper, we present SpecEE, a fast LLM inference engine with…