相关论文: Verification of Bit-Flip Attacks against Quantized…

After being trained, classifiers must often operate on data that has been corrupted by noise. In this paper, we consider the impact of such noise on the features of binary classifiers. Inspired by tools for classifier robustness, we…

Quantizing weights and activations of deep neural networks is essential for deploying them in resource-constrained devices, or cloud platforms for at-scale services. While binarization is a special case of quantization, this extreme case…

In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…

Neural network verification is an active and rapidly maturing research area, with a growing ecosystem of solvers and tools. The VNN-LIB standard was introduced to support interoperability in this ecosystem, but Version~1.0 has several…

With deep learning deployed in many security-sensitive areas, machine learning security is becoming progressively important. Recent studies demonstrate attackers can exploit system-level techniques exploiting the RowHammer vulnerability of…

Motivated by the transformative impact of deep neural networks (DNNs) in various domains, researchers and anti-virus vendors have proposed DNNs for malware detection from raw bytes that do not require manual feature engineering. In this…

Physical Unclonable Functions (PUFs) are modern solutions for cheap and secure key storage. The security level strongly depends on a PUF's unpredictability, which is impaired if certain bits of the PUF response tend towards the same value…

Fault injection attacks represent a type of active, physical attack against cryptographic circuits. Various countermeasures have been proposed to thwart such attacks, the design and implementation of which are, however, intricate,…

With the surge of social media, maliciously tampered public speeches, especially those from influential figures, have seriously affected social stability and public trust. Existing speech tampering detection methods remain insufficient:…

Despite the remarkable capabilities demonstrated by Graph Neural Networks (GNNs) in graph-related tasks, recent research has revealed the fairness vulnerabilities in GNNs when facing malicious adversarial attacks. However, all existing…

With the race to build large-scale quantum computers and efforts to exploit quantum algorithms for efficient problem solving in science and engineering disciplines, the requirement to have efficient and scalable verification methods are of…

Despite the exploding interest in graph neural networks there has been little effort to verify and improve their robustness. This is even more alarming given recent findings showing that they are extremely vulnerable to adversarial attacks…

Our ISCA 2014 paper provided the first scientific and detailed characterization, analysis, and real-system demonstration of what is now popularly known as the RowHammer phenomenon (or vulnerability) in modern commodity DRAM chips, which are…

With the increasing size of frontier LLMs, post-training quantization has become the standard for memory-efficient deployment. Recent work has shown that basic rounding-based quantization schemes pose security risks, as they can be…

Adversarial examples have emerged as a significant threat to machine learning algorithms, especially to the convolutional neural networks (CNNs). In this paper, we propose two quantization-based defense mechanisms, Constant Quantization…

As large-scale quantum computers become a reality, they will likely exist as centralized cloud resources accessible to a broad user base. Securely delegating private quantum computations to untrusted servers is therefore a foundational…

The widely held belief that BQP strictly contains BPP raises fundamental questions: Upcoming generations of quantum computers might already be too large to be simulated classically. Is it possible to experimentally test that these systems…

Quantum computers are becoming increasingly accessible, and may soon outperform classical computers for useful tasks. However, qubit readout errors remain a significant hurdle to running quantum algorithms on current devices. We present a…

Recent advances in neural networks have led to significant computational and memory demands, spurring interest in one-bit weight compression to enable efficient inference on resource-constrained devices. However, the theoretical…

Deepfake detection aims to contrast the spread of deep-generated media that undermines trust in online content. While existing methods focus on large and complex models, the need for real-time detection demands greater efficiency. With this…