相关论文: Test-Time Poisoning Attacks Against Test-Time Adap…

Existing test-time adaptation (TTA) approaches often adapt models with the unlabeled testing data stream. A recent attempt relaxed the assumption by introducing limited human annotation, referred to as Human-In-the-Loop Test-Time Adaptation…

Time-series forecasting has seen significant advancements with the introduction of token prediction mechanisms such as multi-head attention. However, these methods often struggle to achieve the same performance as in language modeling,…

Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However, the existence of adversarial attacks and data poisoning…

Multi-modal test-time adaptation (TTA) enhances the resilience of benchmark multi-modal models against distribution shifts by leveraging the unlabeled target data during inference. Despite the documented success, the advancement of…

In targeted poisoning attacks, an attacker manipulates an agent-environment interaction to force the agent into adopting a policy of interest, called target policy. Prior work has primarily focused on attacks that modify standard MDP…

Test-Time Adaptation (TTA) addresses domain shifts between training and testing. However, existing methods assume a homogeneous target domain (e.g., single domain) at any given time. They fail to handle the dynamic nature of real-world…

Test time adaptation (TTA) equips deep learning models to handle unseen test data that deviates from the training distribution, even when source data is inaccessible. While traditional TTA methods often rely on entropy as a confidence…

Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts. We demonstrate via out-of-distribution (OOD) detection that these high-bias prompts cause a…

The ability to transfer adversarial attacks from one model (the surrogate) to another model (the victim) has been an issue of concern within the machine learning (ML) community. The ability to successfully evade unseen models represents an…

The zero-shot capabilities of Vision-Language Models (VLMs) have been widely leveraged to improve predictive performance. However, previous works on transductive or test-time adaptation (TTA) often make strong assumptions about the data…

We propose a method for test-time adaptation of pretrained depth completion models. Depth completion models, trained on some ``source'' data, often predict erroneous outputs when transferred to ``target'' data captured in novel…

Previous works on depression detection use datasets collected in similar environments to train and test the models. In practice, however, the train and test distributions cannot be guaranteed to be identical. Distribution shifts can be…

Electroencephalography (EEG) foundation models have shown strong potential for learning generalizable representations from large-scale neural data, yet their clinical deployment is hindered by distribution shifts across clinical settings,…

Ensuring the reliability of machine learning-based intrusion detection systems remains a critical challenge in Internet of Things (IoT) environments, particularly as data poisoning attacks increasingly threaten the integrity of model…

Test-time adaptation (TTA) aims to transfer knowledge from a source model to unknown test data with potential distribution shifts in an online manner. Many existing TTA methods rely on entropy as a confidence metric to optimize the model.…

Test-time alignment (TTA) aims to adapt models to specific rewards during inference. However, existing methods tend to either under-optimise or over-optimise (reward hack) the target reward function. We propose Null-Text Test-Time Alignment…

Recent studies have shown that deep learning models are very vulnerable to poisoning attacks. Many defense methods have been proposed to address this issue. However, traditional poisoning attacks are not as threatening as commonly believed.…

Test-Time Adaptation (TTA) aims to tackle distribution shifts using unlabeled test data without access to the source data. In the context of multimodal data, there are more complex noise patterns than unimodal data such as simultaneous…

Protein language models (PLMs) are becoming practical tools for de novo protein design, yet their dual-use potential raises safety concerns. We show that domain adaptation to specific taxonomic groups can elicit toxic protein generation,…

Generally, regularization-based continual learning models limit access to the previous task data to imitate the real-world constraints related to memory and privacy. However, this introduces a problem in these models by not being able to…