Related papers: An Attack on The Speculative Vectorization: Leakag…

We study privacy leakage in the reasoning traces of large reasoning models used as personal agents. Unlike final outputs, reasoning traces are often assumed to be internal and safe. We challenge this assumption by showing that reasoning…

Spectre vulnerabilities violate our fundamental assumptions about architectural abstractions, allowing attackers to steal sensitive data despite previously state-of-the-art countermeasures. To defend against Spectre, developers of…

Since the advent of SPECTRE, a number of countermeasures have been proposed and deployed. Rigorously reasoning about their effectiveness, however, requires a well-defined notion of security against speculative execution attacks, which has…

As a crucial building block in vertical Federated Learning (vFL), Split Learning (SL) has demonstrated its practice in the two-party model training collaboration, where one party holds the features of data samples and another party holds…

We present uSpectre, a new class of transient execution attacks that exploit microcode branch mispredictions to transiently leak sensitive data. We find that many long-known and recently-discovered transient execution attacks, which were…

The transient-execution attack Meltdown leaks sensitive information by transiently accessing inaccessible data during out-of-order execution. Although Meltdown is fixed in hardware for recent CPU generations, most currently-deployed CPUs…

For distributed machine learning with sensitive data, we demonstrate how minimizing distance correlation between raw data and intermediary representations reduces leakage of sensitive raw data patterns across client communications while…

ARM Memory Tagging Extension (MTE) is a new hardware feature introduced in ARMv8.5-A architecture, aiming to detect memory corruption vulnerabilities. The low overhead of MTE makes it an attractive solution to mitigate memory corruption…

The lack of transparency about code datasets used to train large language models (LLMs) makes it difficult to detect, evaluate, and mitigate data leakage. We present a perturbation-based method to quantify memorization advantage in code…

Large language models (LLMs) are increasingly needed for interactive mobile applications, but high-quality models exceed the limited DRAM available on smartphones. Flash storage can hold larger models, yet flash-backed inference is slow…

Speculative execution is an optimization technique that has been part of CPUs for over a decade. It predicts the outcome and target of branch instructions to avoid stalling the execution pipeline. However, until recently, the security…

Cache occupancy attacks exploit the shared nature of cache hierarchies to infer a victim's activities by monitoring overall cache usage, unlike access-driven cache attacks that focus on specific cache lines or sets. There exists some prior…

Distributed machine learning has been widely used in recent years to tackle the large and complex dataset problem. Therewith, the security of distributed learning has also drawn increasing attentions from both academia and industry. In this…

Power-based side-channel is a serious security threat to the System on Chip (SoC). The secret information is leaked from the power profile of the system while a cryptographic algorithm is running. The mitigation requires efforts from both…

With the increasingly giant scales of (causal) large language models (LLMs), the inference efficiency comes as one of the core concerns along the improved performance. In contrast to the memory footprint, the latency bottleneck seems to be…

Speculative decoding (SD) accelerates language model inference by drafting tokens from a cheap proposal model and verifying them against an expensive target model via rejection sampling. Because rejection truncates the draft block at the…

Recently, speculative decoding (SD) has emerged as a promising technique to accelerate LLM inference by employing a small draft model to propose draft tokens in advance, and validating them in parallel with the large target model. However,…

We introduce BLADE, a new approach to automatically and efficiently eliminate speculative leaks from cryptographic code. BLADE is built on the insight that to stop leaks via speculation, it suffices to $\textit{cut}$ the dataflow from…

While cryptographic algorithms such as the ubiquitous Advanced Encryption Standard (AES) are secure, *physical implementations* of these algorithms in hardware inevitably 'leak' sensitive data such as cryptographic keys. A particularly…

Federated learning has emerged as a promising paradigm for collaborative model training while preserving data privacy. However, recent studies have shown that it is vulnerable to various privacy attacks, such as data reconstruction attacks.…