Related papers: Backdoors in Conditional Diffusion: Threats to Res…
An adversarial example is a modified input image designed to cause a Machine Learning (ML) model to make a mistake; these perturbations are often invisible or subtle to human observers and highlight vulnerabilities in a model's ability to…
Recent advancements in deep learning-based compression techniques have surpassed traditional methods. However, deep neural networks remain vulnerable to backdoor attacks, where pre-defined triggers induce malicious behaviors. This paper…
Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of pre-trained language models (PLMs) to specific tasks. By tuning only a minimal set of (extra) parameters, PEFT achieves performance that is comparable to standard…
Backdoor attacks targeting text-to-image diffusion models have advanced rapidly. However, current backdoor samples often exhibit two key abnormalities compared to benign samples: 1) Semantic Consistency, where backdoor prompts tend to…
When machine learning training is outsourced to third parties, $backdoor$ $attacks$ become practical as the third party who trains the model may act maliciously to inject hidden behaviors into the otherwise accurate model. Until now, the…
Vision-Language Models (VLMs) have achieved impressive progress in multimodal text generation, yet their rapid adoption raises increasing concerns about security vulnerabilities. Existing backdoor attacks against VLMs primarily rely on…
Contrastive Language-Image Pre-training (CLIP) on large image-caption datasets has achieved remarkable success in zero-shot classification and enabled transferability to new domains. However, CLIP is extremely more vulnerable to targeted…
Controllable image synthesis models allow creation of diverse images based on text instructions or guidance from a reference image. Recently, denoising diffusion probabilistic models have been shown to generate more realistic imagery than…
Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data. We consider transferable poisoning attacks…
Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…
Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications. A critical flaw in existing methods is that the poison…
Cyber-defense systems are being developed to automatically ingest Cyber Threat Intelligence (CTI) that contains semi-structured data and/or text to populate knowledge graphs. A potential risk is that fake CTI can be generated and spread…
While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can…
In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential…
Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean inputs but misclassifies trigger-carrying inputs to an attacker-chosen target class.…
Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…
Backdoor attacks embed malicious triggers into training data, enabling attackers to manipulate neural network behavior during inference while maintaining high accuracy on benign inputs. However, existing backdoor attacks face limitations…
Diffusion models build a new milestone for image generation yet raising public concerns, for they can be fine-tuned on unauthorized images for customization. Protection based on adversarial attacks rises to encounter this unauthorized…
Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…
Federated Learning (FL) is a decentralized machine learning method that enables participants to collaboratively train a model without sharing their private data. Despite its privacy and scalability benefits, FL is susceptible to backdoor…