相关论文: When One Modality Rules Them All: Backdoor Modalit…

We can often verify the correctness of neural network outputs using ground truth labels, but we cannot reliably determine whether the output was produced by normal or anomalous internal mechanisms. Mechanistic anomaly detection (MAD) aims…

Vision Language Model (VLM) typically assume complete modality input during inference. However, their effectiveness drops sharply when certain modalities are unavailable or incomplete. Current research on missing modality primarily faces…

For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world…

Backdoor attacks have been shown to be a serious security threat against deep learning models, and detecting whether a given model has been backdoored becomes a crucial task. Existing defenses are mainly built upon the observation that the…

LiDAR-based 3D object detection is widely used in safety-critical systems. However, these systems remain vulnerable to backdoor attacks that embed hidden malicious behaviors during training. A key limitation of existing backdoor attacks is…

Three-dimensional molecular generators based on diffusion models can now reach near-crystallographic accuracy, yet they remain fragmented across tasks. SMILES-only inputs, two-stage pretrain-finetune pipelines, and one-task-one-model…

Institutions with limited data and computing resources often outsource model training to third-party providers in a semi-honest setting, assuming adherence to prescribed training protocols with pre-defined learning paradigm (e.g.,…

Multimodal systems are vulnerable to partial or complete loss of input channels at deployment, which undermines reliability in real-world settings. This paper presents ModalImmune, a training framework that enforces modality immunity by…

Multi-modal data-sets are ubiquitous in modern applications, and multi-modal Variational Autoencoders are a popular family of models that aim to learn a joint representation of the different modalities. However, existing approaches suffer…

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

Dataset Condensation (DC) is a data-efficient learning paradigm that synthesizes small yet informative datasets, enabling models to match the performance of full-data training. However, recent work exposes a critical vulnerability of DC to…

Text-to-image diffusion models have revolutionized generative AI, but their vulnerability to backdoor attacks poses significant security risks. Adversaries can inject imperceptible textual triggers into training data, causing models to…

Diffusion models, though originally designed for generative tasks, have demonstrated impressive self-supervised representation learning capabilities. A particularly intriguing phenomenon in these models is the emergence of unimodal…

Visual content understanding frequently relies on multi-task models to extract robust representations of a single visual input for multiple downstream tasks. However, in comparison to extensively studied single-task models, the adversarial…

Despite the notable advancements and versatility of multi-modal diffusion models, such as text-to-image models, their susceptibility to adversarial inputs remains underexplored. Contrary to expectations, our investigations reveal that the…

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…

Speech language models (SLMs) are systems of systems: independent components that unite to achieve a common goal. Despite their heterogeneous nature, SLMs are often studied end-to-end; how information flows through the pipeline remains…

Multimodal learning often outperforms its unimodal counterparts by exploiting unimodal contributions and cross-modal interactions. However, focusing only on integrating multimodal features into a unified comprehensive representation…

As audio-visual multi-modal large language models (MLLMs) are increasingly deployed in safety-critical applications, understanding their vulnerabilities is crucial. To this end, we introduce Multi-Modal Typography, a systematic study…

Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and services. However, the untrustworthy third-party LLMs may…