Related papers: Narrow Secret Loyalty Dodges Black-Box Audits
Third-party resources ($e.g.$, samples, backbones, and pre-trained models) are usually involved in the training of deep neural networks (DNNs), which brings backdoor attacks as a new training-phase threat. In general, backdoor attackers…
The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…
Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…
In a backdoor attack on a machine learning model, an adversary produces a model that performs well on normal inputs but outputs targeted misclassifications on inputs containing a small trigger pattern. Model compression is a widely-used…
The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries…
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…
Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…
Differential privacy (DP) offers a theoretical upper bound on the potential privacy leakage of analgorithm, while empirical auditing establishes a practical lower bound. Auditing techniques exist forDP training algorithms. However machine…
We show that continual pretraining on plausible misinformation can overwrite specific factual knowledge in large language models without degrading overall performance. Unlike prior poisoning work under static pretraining, we study repeated…
Approximate machine unlearning aims to remove the effect of specific data from trained models to ensure individuals' privacy. Existing methods focus on the removed records and assume the retained ones are unaffected. However, recent studies…
Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on…
We uncover a latent capacity for introspection in a Qwen 32B model, demonstrating that the model can detect when concepts have been injected into its earlier context and identify which concept was injected. While the model denies injection…
Deep learning models are vulnerable to various adversarial manipulations of their training data, parameters, and input sample. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model,…
Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour. For instance, backdoors can be implanted through crafting training instances with a specific…
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.…
Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…
As the capacity of deep neural networks (DNNs) increases, their need for huge amounts of data significantly grows. A common practice is to outsource the training process or collect more data over the Internet, which introduces the risks of…
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…
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries embed a hidden backdoor trigger during the training process for malicious prediction manipulation. These attacks pose great threats to the applications of…
Neural networks trained on real-world data often exhibit biases while simultaneously being vulnerable to privacy attacks aimed at extracting sensitive information. Despite extensive research on each problem individually, their intersection…