Related papers: GradSentry: Gradient Spectral Entropy for Backdoor…
Despite the notable success of language models (LMs) in various natural language processing (NLP) tasks, the reliability of LMs is susceptible to backdoor attacks. Prior research attempts to mitigate backdoor learning while training the LMs…
Backdoor attacks have emerged as a prominent threat to natural language processing (NLP) models, where the presence of specific triggers in the input can lead poisoned models to misclassify these inputs to predetermined target classes.…
Deep learning models have been shown to be vulnerable to adversarial attacks. In particular, gradient-based attacks have demonstrated high success rates recently. The gradient measures how each image pixel affects the model output, which…
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,…
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the…
Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…
Poison-only Clean-label Backdoor Attacks aim to covertly inject attacker-desired behavior into DNNs by merely poisoning the dataset without changing the labels. To effectively implant a backdoor, multiple \textbf{triggers} are proposed for…
Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…
Backdoor attacks poison the training data, causing the model to behave normally on clean inputs but predict attacker-chosen labels when trigger patterns are embedded into the input samples. Defending against such attacks is highly…
Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…
Predicitions made by neural networks can be fraudulently altered by so-called poisoning attacks. A special case are backdoor poisoning attacks. We study suitable detection methods and introduce a new method called Heatmap Clustering. There,…
Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third party or resort to publicly available pre-trained models.…
Federated learning collaboratively trains a neural network on a global server, where each local client receives the current global model weights and sends back parameter updates (gradients) based on its local private data. The process of…
Contrastive language-image pretraining (CLIP) has been found to be vulnerable to poisoning backdoor attacks where the adversary can achieve an almost perfect attack success rate on CLIP models by poisoning only 0.01\% of the training…
In recent years, attention-based models have excelled across various domains but remain vulnerable to backdoor attacks, often from downloading or fine-tuning on poisoned datasets. Many current methods to mitigate backdoors in NLP models…
Training deep neural networks requires gradient estimation from data batches to update parameters. Gradients per parameter are averaged over a set of data and this has been presumed to be safe for privacy-preserving training in joint,…
The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…
As Large Language Models (LLMs) become integral software components in modern applications, unauthorized model derivations through fine-tuning, merging, and redistribution have emerged as critical software engineering challenges. Unlike…
Deep Neural Networks (DNNs) are susceptible to backdoor attacks during training. The model corrupted in this way functions normally, but when triggered by certain patterns in the input, produces a predefined target label. Existing defenses…
Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…