Related papers: GATEBLEED: Exploiting On-Core Accelerator Power Ga…

Dynamic quantization emerged as a practical approach to increase the utilization and efficiency of the machine learning serving flow. Unlike static quantization, which applies quantization offline, dynamic quantization operates on tensors…

Now a days, power has become a primary consideration in hardware design, and is critical in computer systems especially for portable devices with high performance and more functionality. Clock-gating is the most common technique used for…

Caches on the modern commodity CPUs have become one of the major sources of side-channel leakages and been abused as a new attack vector. To thwart the cache-based side-channel attacks, two types of countermeasures have been proposed:…

Timing channels in cache hierarchies are an important enabler in many microarchitectural attacks. ScatterCache (USENIX 2019) is a protected cache architecture that randomizes the address-to-index mapping with a keyed cryptographic function,…

For a distributed last-level cache (LLC) in a large multicore chip, the access time to one LLC bank can significantly differ from that to another due to the difference in physical distance. In this paper, we successfully demonstrated a new…

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…

Searchable encryption (SE) is one of the key enablers for building encrypted databases. It allows a cloud server to search over encrypted data without decryption. Dynamic SE additionally includes data addition and deletion operations to…

Users' website browsing history contains sensitive information, like health conditions, political interests, financial situations, etc. Some recent studies have demonstrated the possibility of inferring website fingerprints based on…

Explainable Artificial Intelligence (XAI) is a crucial pathway in mitigating the risk of non-transparency in the decision-making process of black-box Artificial Intelligence (AI) systems. However, despite the benefits, XAI methods are found…

Federated Learning (FL) enables collaborative model building among a large number of participants without the need for explicit data sharing. But this approach shows vulnerabilities when privacy inference attacks are applied to it. In…

Recent studies highlighting the vulnerability of computer architecture to information leakage attacks have been a cause of significant concern. Among the various classes of microarchitectural attacks, cache timing channels are especially…

Retrieval-Augmented Generation (RAG) empowers LLMs with external knowledge, making cross-institutional domain-specific knowledge base integration a highly promising deployment paradigm. Despite this potential, strict privacy regulations…

Per Row Activation Counting (PRAC) has emerged as a robust framework for mitigating RowHammer (RH) vulnerabilities in modern DRAM systems. However, we uncover a critical vulnerability: a timing channel introduced by the Alert Back-Off (ABO)…

With the rapid progress of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts. Though model developers and researchers work hard on dialog safety to avoid generating harmful content from…

We introduce IMPACT, a set of high-throughput main memory-based timing attacks that leverage characteristics of processing-in-memory (PiM) architectures to establish covert and side channels. IMPACT enables high-throughput communication and…

Federated Learning (FL) enables collaborative model training across distributed devices while safeguarding data and user privacy. However, FL remains susceptible to privacy threats that can compromise data via direct means. That said,…

Cache randomization has recently been revived as a promising defense against conflict-based cache side-channel attacks. As two of the latest implementations, CEASER-S and ScatterCache both claim to thwart conflict-based cache side-channel…

In heterogeneous SoCs, accelerators like integrated GPUs (iGPUs) are integrated on the same chip as CPUs, sharing the memory subsystem. In such systems, the massive memory requests from throughput-oriented accelerators significantly…

Trusted execution environments in several existing and upcoming CPUs demonstrate the success of confidential computing, with the caveat that tenants cannot securely use accelerators such as GPUs and FPGAs. In this paper, we reconsider the…

Side-channel attacks pose serious threats to many security models, especially sandbox-based browsers. While transient-execution side channels in out-of-order processors have previously been blamed for vulnerabilities such as Spectre and…