Related papers: Comprehensive Kernel Safety in the Spectre Era: Mi…

It is by now well-established that modern over-parameterized models seem to elude the bias-variance tradeoff and generalize well despite overfitting noise. Many recent works attempt to analyze this phenomenon in the relatively tractable…

As cache-based side-channel attacks become serious security problems, various defenses have been proposed and deployed in both software and hardware. Consequently, cache-based side-channel attacks on processes co-residing on the same core…

Real-time systems have recently been shown to be vulnerable to timing inference attacks, mainly due to their predictable behavioral patterns. Existing solutions such as schedule randomization lack the ability to protect against such…

We study the problem of scheduling jobs on fault-prone machines communicating via a shared channel, also known as multiple-access channel. We have $n$ arbitrary length jobs to be scheduled on $m$ identical machines, $f$ of which are prone…

Quantum computing promises to revolutionize machine learning, offering significant efficiency gains in tasks such as clustering and distance estimation. Additionally, it provides enhanced security through fundamental principles like the…

The certification of randomness is essential for both fundamental science and information technologies. Unlike traditional random number generators, randomness obtained from nonlocal correlations is fundamentally guaranteed to be…

We present a performance model for bandwidth limited loop kernels which is founded on the analysis of modern cache based microarchitectures. This model allows an accurate performance prediction and evaluation for existing instruction codes.…

Deployed large language models (LLMs) often rely on speculative decoding, a technique that generates and verifies multiple candidate tokens in parallel, to improve throughput and latency. In this work, we reveal a new side-channel whereby…

Spectre v1 attacks pose a substantial threat to security-critical software, particularly cryptographic implementations. Existing software mitigations, however, often introduce excessive overhead by indiscriminately hardening instructions…

The openness of modern IT systems and their permanent change make it challenging to keep these systems secure. A combination of regression and security testing called security regression testing, which ensures that changes made to a system…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Speculative side-channel attacks access sensitive data and use transmitters to leak the data during wrong-path execution. Various defenses have been proposed to prevent such information leakage. However, not all speculatively executed…

Separation kernels provide temporal/spatial separation and controlled information flow to their hosted applications. They are introduced to decouple the analysis of applications in partitions from the analysis of the kernel itself. More…

The wide deployment of Large Language Models (LLMs) has given rise to strong demands for optimizing their inference performance. Today's techniques serving this purpose primarily focus on reducing latency and improving throughput through…

The vulnerability of models to data aberrations and adversarial attacks influences their ability to demarcate distinct class boundaries efficiently. The network's confidence and uncertainty play a pivotal role in weight adjustments and the…

Obtaining reliable, adaptive confidence sets for prediction functions (hypotheses) is a central challenge in sequential decision-making tasks, such as bandits and model-based reinforcement learning. These confidence sets typically rely on…

Sequential self-attention models usually rely on additive positional embeddings, which inject positional information into item representations at the input. In the absence of positional signals, the attention block is…

The work by Christandl, K\"onig and Renner [Phys. Rev. Lett. 102, 020504 (2009)] provides in particular the possibility of studying unconditional security in the finite-key regime for all discrete-variable protocols. We spell out this bound…

Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…

Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ…