Related papers: On Cryptographic Attacks Using Backdoors for SAT

Machine Learning using neural networks has received prominent attention recently because of its success in solving a wide variety of computational tasks, in particular in the field of computer vision. However, several works have drawn…

Automated reasoners, such as SAT/SMT solvers and first-order provers, are becoming the backbones of rigorous systems engineering, being used for example in applications of system verification, program synthesis, and cybersecurity.…

Backdoor attacks occur when an attacker subtly manipulates machine learning models during the training phase, leading to unintended behaviors when specific triggers are present. To mitigate such emerging threats, a prevalent strategy is to…

Speaker verification has been widely and successfully adopted in many mission-critical areas for user identification. The training of speaker verification requires a large amount of data, therefore users usually need to adopt third-party…

Backdoor attacks have become a major security threat for deploying machine learning models in security-critical applications. Existing research endeavors have proposed many defenses against backdoor attacks. Despite demonstrating certain…

Recent studies have proposed integrating Chain-of-Thought (CoT) reasoning to further enhance the reliability of Code Language Models (CLMs) in generating code, a step-by-step approach that breaks down complex programming tasks into…

In recent years, neural backdoor attack has been considered to be a potential security threat to deep learning systems. Such systems, while achieving the state-of-the-art performance on clean data, perform abnormally on inputs with…

The Boolean SATisfiability problem (SAT) is of central importance in computer science. Although SAT is known to be NP-complete, progress on the engineering side, especially that of Conflict-Driven Clause Learning (CDCL) and Local Search SAT…

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…

The security of logic locking has been called into question by various attacks, especially a Boolean satisfiability (SAT) based attack, that exploits scan access in a working chip. Among other techniques, a robust design-for-security (DFS)…

Gate camouflaging is a known security enhancement technique that tries to thwart reverse engineering by hiding the functions of gates or the connections between them. A number of works on SAT-based attacks have shown that it is often…

Deep Learning backdoor attacks have a threat model similar to traditional cyber attacks. Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks. In this paper,…

The Boolean satisfiability (SAT) problem lies at the core of many applications in combinatorial optimization, software verification, cryptography, and machine learning. While state-of-the-art solvers have demonstrated high efficiency in…

Deep learning achieves outstanding results in many machine learning tasks. Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model. The modified training samples…

Backdoor attacks have been shown to impose severe threats to real security-critical scenarios. Although previous works can achieve high attack success rates, they either require access to victim models which may significantly reduce their…

Propositional satisfiability (SAT) is one of the most fundamental problems in computer science. Its worst-case hardness lies at the core of computational complexity theory, for example in the form of NP-hardness and the (Strong) Exponential…

Backdoor attacks have become an emerging threat to NLP systems. By providing poisoned training data, the adversary can embed a "backdoor" into the victim model, which allows input instances satisfying certain textual patterns (e.g.,…

Recent years have shown that more than ever governments and intelligence agencies try to control and bypass the cryptographic means used for the protection of data. Backdooring encryption algorithms is considered as the best way to enforce…

Recently, a series of pioneer studies have shown the potency of pre-trained models in sequential recommendation, illuminating the path of building an omniscient unified pre-trained recommendation model for different downstream…

Graph neural network (GNN) have demonstrated exceptional performance in solving critical problems across diverse domains yet remain susceptible to backdoor attacks. Existing studies on backdoor attack for graph classification are limited to…