Related papers: TRIGS: Trojan Identification from Gradient-based S…

With tools like GitHub Copilot, automatic code suggestion is no longer a dream in software engineering. These tools, based on large language models, are typically trained on massive corpora of code mined from unvetted public sources. As a…

This work corroborates a run-time Trojan detection method exploiting STRong Intentional Perturbation of inputs, is a multi-domain Trojan detection defence across Vision, Text and Audio domains---thus termed as STRIP-ViTA. Specifically,…

The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI Trojans. These AI trojans are malicious, hidden backdoors…

Self-supervised learning (SSL) is a prevalent approach for encoding data representations. Using a pre-trained SSL image encoder and subsequently training a downstream classifier, impressive performance can be achieved on various tasks with…

Model stealing attacks present a dilemma for public machine learning APIs. To protect financial investments, companies may be forced to withhold important information about their models that could facilitate theft, including uncertainty…

Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. Provably bounding model behavior under such attacks remains…

The widespread deployment of deep learning models in privacy-sensitive domains has amplified concerns regarding privacy risks, particularly those stemming from gradient leakage during training. Current privacy assessments primarily rely on…

The threat of hardware Trojans (HTs) and their detection is a widely studied field. While the effort for inserting a Trojan into an application-specific integrated circuit (ASIC) can be considered relatively high, especially when trusting…

We target the problem of detecting Trojans or backdoors in DNNs. Such models behave normally with typical inputs but produce specific incorrect predictions for inputs poisoned with a Trojan trigger. Our approach is based on a novel…

Machine learning models often pose a threat to the privacy of individuals whose data is part of the training set. Several recent attacks have been able to infer sensitive information from trained models, including model inversion or…

Emerging self-supervised learning (SSL) has become a popular image representation encoding method to obviate the reliance on labeled data and learn rich representations from large-scale, ubiquitous unlabelled data. Then one can train a…

Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers,…

In this paper, we propose a new first-order gradient-based algorithm to train deep neural networks. We first introduce the sign operation of stochastic gradients (as in sign-based methods, e.g., SIGN-SGD) into ADAM, which is called as…

We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train…

Hardware Trojans (HTs) are undesired design or manufacturing modifications that can severely alter the security and functionality of digital integrated circuits. HTs can be inserted according to various design criteria, e.g., nets switching…

Hardware trojan detection methods, based on machine learning (ML) techniques, mainly identify suspected circuits but lack the ability to explain how the decision was arrived at. An explainable methodology and architecture is introduced…

In recent years, machine learning models have been shown to be vulnerable to backdoor attacks. Under such attacks, an adversary embeds a stealthy backdoor into the trained model such that the compromised models will behave normally on clean…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Artificial Intelligence (AI) relies heavily on deep learning - a technology that is becoming increasingly popular in real-life applications of AI, even in the safety-critical and high-risk domains. However, it is recently discovered that…

Recent advances in Trajectory Optimization (TO) models have achieved remarkable success in offline reinforcement learning. However, their vulnerabilities against backdoor attacks are poorly understood. We find that existing backdoor attacks…