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

Spectre attacks exploit microprocessor speculative execution to read and transmit forbidden data outside the attacker's trust domain and sandbox. Recent hardware schemes allow potentially-unsafe speculative accesses but prevent the secret's…

Efficient LLM inference on resource-constrained devices presents significant challenges in compute and memory utilization. Due to limited GPU memory, existing systems offload model weights to CPU memory, incurring substantial I/O overhead…

Watermarking plays a key role in the provenance and detection of AI-generated content. While existing methods prioritize robustness against real-world distortions (e.g., JPEG compression and noise addition), we reveal a fundamental…

Code secrets are sensitive assets for software developers, and their leakage poses significant cybersecurity risks. While the rapid development of AI code assistants powered by Code Large Language Models (CLLMs), CLLMs are shown to…

Speculative decoding is an effective method for lossless acceleration of large language models during inference. It uses a fast model to draft a block of tokens which are then verified in parallel by the target model, and provides a…

Machine learning (ML) has been widely adopted in various privacy-critical applications, e.g., face recognition and medical image analysis. However, recent research has shown that ML models are vulnerable to attacks against their training…

Model extraction attacks are designed to steal trained models with only query access, as is often provided through APIs that ML-as-a-Service providers offer. Machine Learning (ML) models are expensive to train, in part because data is hard…

The problem of publishing privacy-guaranteed data for hypothesis testing is studied using the maximal leakage (ML) as a metric for privacy and the type-II error exponent as the utility metric. The optimal mechanism (random mapping) that…

In the last two decades, the evolving cyber-threat landscape has brought to center stage the contentious tradeoffs between the security and performance of modern microprocessors. The guarantees provided by the hardware to ensure no…

Selective data protection is a promising technique to defend against the data leakage attack. In this paper, we revisit technical challenges that were neglected when applying this protection to real applications. These challenges include…

Cache timing attacks allow attackers to infer the properties of a secret execution by observing cache hits and misses. But how much information can actually leak through such attacks? For a given program, a cache model, and an input, our…

We propose ProSpeCT, a generic formal processor model providing provably secure speculation for the constant-time policy. For constant-time programs under a non-speculative semantics, ProSpeCT guarantees that speculative and out-of-order…

Hyperdimensional Computing (HDC) is facing infringement issues due to straightforward computations. This work, for the first time, raises a critical vulnerability of HDC, an attacker can reverse engineer the entire model, only requiring the…

Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft. A larger target model then reviews this draft to align with its output, and any…

Twenty-eight within-subject counterfactual experiments across 2,047 tabular datasets, plus a boundary experiment on 129 temporal datasets, measuring the severity of four data leakage classes in machine learning. Class I (estimation -…

In contrast to electronic computation, chemical computation is noisy and susceptible to a variety of sources of error, which has prevented the construction of robust complex systems. To be effective, chemical algorithms must be designed…

Research on transient execution attacks including Spectre and Meltdown showed that exception or branch misprediction events might leave secret-dependent traces in the CPU's microarchitectural state. This observation led to a proliferation…

As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a practical paradigm. Prior work has examined the safety and misuse risks associated with agents.…

Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…

Query expansion methods powered by large language models (LLMs) have demonstrated effectiveness in zero-shot retrieval tasks. These methods assume that LLMs can generate hypothetical documents that, when incorporated into a query vector,…