Related papers: Triggerless Backdoor Attack for NLP Tasks with Cle…
Backdoor attacks have been widely studied to hide the misclassification rules in the normal models, which are only activated when the model is aware of the specific inputs (i.e., the trigger). However, despite their success in the…
Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token level and lack deeper semantic manipulation, which limits stealthiness. In addition, Prior…
Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…
The backdoor attack poses a new security threat to deep neural networks. Existing backdoor often relies on visible universal trigger to make the backdoored model malfunction, which are not only usually visually suspicious to human but also…
Backdoor attacks pose a critical threat to machine learning models, causing them to behave normally on clean data but misclassify poisoned data into a poisoned class. Existing defenses often attempt to identify and remove backdoor neurons…
Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models…
In the domain of backdoor attacks, accurate labeling of injected data is essential for evading rudimentary detection mechanisms. This imperative has catalyzed the development of clean-label attacks, which are notably more elusive as they…
Backdoor attacks, in which a model behaves maliciously when given an attacker-specified trigger, pose a major security risk for practitioners who depend on publicly released language models. As a countermeasure, backdoor detection methods…
Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch.…
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…
In recent years, there has been an explosive growth in multimodal learning. Image captioning, a classical multimodal task, has demonstrated promising applications and attracted extensive research attention. However, recent studies have…
Modern graph learning systems often combine links with text, as in citation networks with abstracts or social graphs with user posts. In such systems, text is usually easier to edit than graph structure, which creates a practical security…
Backdoor attacks pose a significant threat to deep neural networks, as backdoored models would misclassify poisoned samples with specific triggers into target classes while maintaining normal performance on clean samples. Among these,…
Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…
Recent research shows deep neural networks are vulnerable to different types of attacks, such as adversarial attack, data poisoning attack and backdoor attack. Among them, backdoor attack is the most cunning one and can occur in almost…
Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…
Language Models (LMs) are becoming increasingly popular in real-world applications. Outsourcing model training and data hosting to third-party platforms has become a standard method for reducing costs. In such a situation, the attacker can…
Genomic foundation models trained on DNA sequences have demonstrated remarkable capabilities across diverse biological tasks, from variant effect prediction to genome design. These models are typically trained on massive, publicly sourced…
Adversarial attacks alter NLP model predictions by perturbing test-time inputs. However, it is much less understood whether, and how, predictions can be manipulated with small, concealed changes to the training data. In this work, we…
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…