相关论文: Spill The Beans: Exploiting CPU Cache Side-Channel…

Privacy leakage in LLM agents is often studied through individual storage or execution components, such as memory modules, retrieval pipelines, or tool-mediated artifacts. However, these settings are typically analyzed in isolation, making…

The remarkable performance of large language models (LLMs) in generation tasks has enabled practitioners to leverage publicly available models to power custom applications, such as chatbots and virtual assistants. However, the data used to…

Large Language Models (LLMs) have shown greatly enhanced performance in recent years, attributed to increased size and extensive training data. This advancement has led to widespread interest and adoption across industries and the public.…

The rapid adoption of large language models (LLMs) in critical domains has spurred extensive research into their security issues. While input manipulation attacks (e.g., prompt injection) have been well studied, Bit-Flip Attacks (BFAs) --…

Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing backdoor attacks on LVLMs aim to force the victim model to…

Conversational assistants are increasingly integrating long-term memory with large language models (LLMs). This persistence of memories, e.g., the user is vegetarian, can enhance personalization in future conversations. However, the same…

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…

Trusted execution environments (TEEs) provide an environment for running workloads in the cloud without having to trust cloud service providers, by offering additional hardware-assisted security guarantees. However, main memory encryption…

Over the last two decades, the danger of sharing resources between programs has been repeatedly highlighted. Multiple side-channel attacks, which seek to exploit shared components for leaking information, have been devised, mostly targeting…

Searchable Symmetric Encryption (SSE) enables efficient search capabilities over encrypted data, allowing users to maintain privacy while utilizing cloud storage. However, SSE schemes are vulnerable to leakage attacks that exploit access…

Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of…

Modern computer processors use microarchitectural optimization mechanisms to improve performance. As a downside, such optimizations are prone to introducing side-channel vulnerabilities. Speculative loading of memory, called prefetching, is…

Recent progress in artificial intelligence (AI), particularly in the domain of large language models (LLMs), has resulted in powerful and versatile dual-use systems. This intelligence can be put towards a wide variety of beneficial tasks,…

Amid the expanding use of pre-training data, the phenomenon of benchmark dataset leakage has become increasingly prominent, exacerbated by opaque training processes and the often undisclosed inclusion of supervised data in contemporary…

Last-level cache side-channel attacks have been mostly demonstrated in highly-controlled, quiescent local environments. Hence, it is unclear whether such attacks are feasible in a production cloud environment. In the cloud, side channels…

Intel Software Guard Extension (SGX) offers software applications enclave to protect their confidentiality and integrity from malicious operating systems. The SSL/TLS protocol, which is the de facto standard for protecting transport-layer…

Side channel attacks steal secret keys by cleverly leveraging information leakages and can, therefore, break encryption. Thus, detection and mitigation of side channel attacks is a very important problem, but the solutions proposed in the…

The training process of large language models (LLMs) often involves varying degrees of test data contamination. Although current LLMs are achieving increasingly better performance on various benchmarks, their performance in practical…

Large language models (LLMs) represent significant breakthroughs in artificial intelligence and hold potential for applications within smart grids. However, as demonstrated in previous literature, AI technologies are susceptible to various…

Modern x86 processors have many prefetch instructions that can be used by programmers to boost performance. However, these instructions may also cause security problems. In particular, we found that on Intel processors, there are two…