Singapore

The rapid advancement of audio generation technologies has escalated the risks of malicious deepfake audio across speech, sound, singing voice, and music, threatening multimedia security and trust. While existing countermeasures (CMs) perform well in single-type audio deepfake detection (ADD), their performance declines in cross-type scenarios. This paper is dedicated to studying the all-type ADD task. We are the first to comprehensively establish an all-type ADD benchmark to evaluate current CMs, incorporating cross-type deepfake
detection across speech, sound, singing voice, and music. Then, we introduce the prompt tuning self-supervised learning (PT-SSL) training paradigm, which optimizes SSL front-end by learning specialized prompt tokens for ADD, requiring 458× fewer trainable parameters than fine-tuning (FT). Considering the auditory perception of different audio types, we propose the wavelet prompt tuning (WPT)-SSL method to capture type-invariant auditory deepfake information from the frequency domain without requiring additional training parameters, thereby enhancing performance over FT in the all-type ADD task. To achieve an universally CM, we utilize all types of deepfake audio for co-training. Experimental results demonstrate that WPT-XLSR-AASIST achieved the best performance, with an average EER of 3.58% across all evaluation sets.

AAAI 2026

Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception

poster

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.<br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

Developing a multi-modal language model capable of understanding 3D scenes remains challenging due to the limited availability of 3D training data, in contrast to the abundance of 2D datasets used for vision-language models (VLMs). As an alternative, we introduce LLaVA³ (pronounced LLaVA Cube), a novel method that improves the 3D scene understanding capabilities of VLMs using only multi-view 2D images, and without requiring any fine-tuning. Inspired by Cubist painters, who represented multiple viewpoints of a 3D object within a single 2D picture, we propose to describe the 3D scene for the VLM through omnidirectional visual representations of each object.
These representations are derived from an intermediate multi-view 3D reconstruction of the scene. Extensive experiments on 3D visual question answering and 3D language grounding show that our approach significantly outperforms previous 2D-based VLM solutions.

LLaVA³: Representing 3D Scenes Like a Cubist Painter to Boost 3D Scene Understanding of VLMs

Existing audio adversarial attack methods suffer from poor transferability, primarily due to insufficient exploration of model decision mechanisms and overreliance on heuristic-driven algorithm design. This paper aims to alleviate this gap.
Specifically, through observations across three mainstream audio tasks (Automatic Speech Recognition, Speaker Verification, and Keyword Spotting), we reveal that these models primarily rely on local temporal features—inputs with time shuffled retain 83.7% of original accuracy. The SHAP-based visualization further validated that time shuffle leads to a significant shift in the salient regions of the model, but the samples can still be correctly identified, indicating the presence of redundant features that can affect decision-making.
Inspired by these findings, we propose Time-Shuffle (TS) adversarial attack (including segments-based TS and phoneme-level-based TS-p). This method divides audio or phonemes into segments, randomly shuffles them, and computes gradients on the shuffled structure.
By forcing perturbations to exploit transferable local temporal features and reduce overfitting to source-specific patterns, TS/TS-p inherently enhances transferability. As a model-agnostic framework, TS/TS-p can seamlessly integrate with existing attack methods.
Comprehensive experiments demonstrate that TS-p achieved SOTA and boosts transferability by about 23%/14.7%/6.3% on ASR/ASV/KWS.

Time Shuffle: A Transferability-Booster for Multiple Audio Adversarial Tasks

At present, spectral clustering is an important branch of unsupervised learning, and its application in deep learning has been widely concerned. However, for high-dimensional sparse datasets, the complexity of network scale leads to parameter explosion, and static Gaussian kernel often has wrong preset data structure. To overcome these challenges, we propose a novel deep clustering model, Deep Clustering Based on Sparse Kolmogorov-Arnold Network (KAN) and Spectral Constraint. It contains a deep sparse clustering framework, in which sparse KAN and the orthogonal layer are designed to enhance the sparsity of the activation function matrix, reduce the number of parameters and improve the stability of model convergence. Additionally, we add an adaptive optimized affinity matrix based on spectral constraint, which overcomes the limitations of static Gaussian kernels, and improves the performance and stability of spectral constraint. Experimental results on both synthetic and real datasets demonstrate that our model outperforms existing methods in clustering performance, computational efficiency, and stability.

Deep Clustering Based on Sparse Kolmogorov-Arnold Network and Spectral Constraint

Latent Diffusion Models have become a powerful tool for generating high-fidelity unrestricted adversarial examples. However, the existing methods typically perturb only the initial latent or rely on prompt engineering, which is ill-suited to the iterative nature of the diffusion process, plus optimization instability due to external text prompts and cumulative drift that push the adversarial images off the data manifold. In this paper, we propose a hierarchical attack framework that operates in alignment with the model's generative manifold and leverages intermediate denoising states to maximize attack transferability and visual fidelity. Extensive experiments show that the proposed attack improves adversarial transferability by $10$-$20$\% against a diverse set of normally-trained models and achieves over 10.5\% higher success rate against adversarially-defended models, while simultaneously enhancing visual quality by $1.0$-$1.2$ FID reduction and 16.7\% LPIPS improvements.

Beyond Single-Point Perturbation: A Hierarchical, Manifold-Aware Approach to Diffusion Attacks

Learning Curve Extrapolation (LCE) is a critical technique for accelerating automated machine learning by terminating unpromising training runs early. Recent state-of-the-art methods have improved predictive accuracy by incorporating contextual information, such as neural network architecture. However, these approaches, whether context-agnostic or architecture-aware, still operate under the implicit assumption of a uniform task landscape. They overlook a pivotal, complementary factor: the intrinsic difficulty of the learning task itself. This oversight leads to a significant degradation in performance, especially for tasks whose learning dynamics diverge from the model's priors. In this work, we argue that task difficulty is a crucial yet neglected dimension for robust LCE. We introduce a novel framework, Difficulty-Adaptive Learning Curve Extrapolation (DA-LCE), which explicitly conditions its predictions on task complexity. Our core contributions are threefold: (1) We propose a transparent, {rule-based method} to quantify task difficulty from the early shape of learning curves, eliminating the need for external meta-features. (2) We design a novel data generation pipeline using a {conditional diffusion model} to create a high-fidelity, difficulty-conditioned synthetic prior for training. (3) We introduce a {Conditional Difficulty-aware PFN (CD-PFN)} that leverages this information to achieve superior predictive accuracy. Extensive experiments on a wide range of benchmarks demonstrate that our CD-PFN significantly outperforms both difficulty-agnostic baselines and even state-of-the-art architecture-aware models. This result highlights that task difficulty is a powerful, complementary source of information, whose impact can be as significant as, or even greater than, that of the model architecture.

Difficulty-Aware Learning Curve Extrapolation

Spiking Neural Networks (SNNs) are emerging as a promising energy-efficient alternative to Artificial Neural Networks (ANNs) due to their event-driven computation paradigm. However, recent advances toward large-scale high-performance SNNs inevitably lead to substantial memory and computational overhead. While quantization offers a potential solution, many quantization approaches fail to deliver verifiable efficiency gains on resource-constrained hardware platforms. In this paper, we propose a lightweight and hardware-friendly SNN that applies quantization to both weights and membrane potentials, termed HardF-SNN. Specifically, we first build a baseline model that adopts shared-scale quantization and batch normalization (BN) folding to simulate integer-only inference during training, since this baseline model has not been thoroughly discussed in previous SNN work. Although the baseline enables integer-arithmetic-only inference, it suffers from performance degradation and may even lead to training failure. To address these issues, we thoroughly analyze the problems caused by quantization and BN folding, and propose solutions to enhance the baseline’s performance. Specifically, we introduce proportional shared-scale quantization to enhance the representation capability, and propose an integer-only BN method to stabilize training convergence through integer arithmetic and bit-shifting operations. Extensive experiments show that HardF-SNN achieves an optimal balance between performance and efficiency, exhibiting excellent compatibility with mainstream hardware accelerators. To demonstrate its effectiveness on resource-constrained platforms, HardF-SNN is deployed on a dedicated FPGA-based hardware accelerator. Evaluation results indicate that our implementation surpasses current state-of-the-art accelerators.

HardF-SNN: Hardware-Friendly Quantization for Spiking Neural Networks with Efficient Integer-Arithmetic-Only Inference

Federated learning (FL) protects data privacy by enabling distributed model training without direct access to client data. However, its distributed nature makes it vulnerable to model and data poisoning attacks. While numerous defenses filter malicious clients using statistical metrics, they overlook the role of model redundancy, where not all parameters contribute equally to the model/attack performance. Current attacks manipulate all model parameters uniformly, making them more detectable, while defenses focus on the overall statistics of client updates, leaving gaps for more sophisticated attacks. We propose an attack-agnostic augmentation method to enhance the stealthiness and effectiveness of existing poisoning attacks in FL, exposing flaws in current defenses and highlighting the need for fine-grained FL security. Our three-stage methodology—pill construction, pill poisoning, and pill injection—injects poison into a compact subnet (i.e., pill) of the global model during the iterative FL training. Experimental results show that FL poisoning attacks enhanced by our method can bypass 8 state-of-the-art (SOTA) defenses, gaining an up to 7x error rate increase, as well as on average a more than 2x error rate increase on both IID and non-IID data, in both cross-silo and cross-device FL systems.

Poisoning with a Pill: Circumventing Detection in Federated Learning

Panoramic video generation has attracted growing attention due to its applications in virtual reality and immersive media.
However, existing methods lack explicit motion control and struggle to generate scenes with large and complex motions.
We propose PanFlow, a novel approach that exploits the spherical nature of panoramas to decouple the highly dynamic camera rotation from the input optical flow condition, enabling more precise control over large and dynamic motions.
We further introduce a spherical noise warping strategy to promote loop consistency in motion across panorama boundaries.
To support effective training, we curate a large-scale, motion-rich panoramic video dataset with frame-level pose and flow annotations.
We also showcase the effectiveness of our method in various applications, including motion transfer and video editing.
Extensive experiments demonstrate that PanFlow significantly outperforms prior methods in motion fidelity, visual quality, and temporal coherence.

PanFlow: Decoupled Motion Control for Panoramic Video Generation

Aiming to identify precise evidence sources from visual documents, visual evidence attribution for visual document retrieval–augmented generation (VD-RAG) ensures reliable and verifiable predictions from vision-language models (VLMs) in multimodal question answering. Most existing methods adopt end-to-end training to facilitate intuitive answer verification. However, they lack fine-grained supervision and progressive traceability throughout the reasoning process. In this paper, we introduce the Chain-of-Evidence (CoE) paradigm for VD-RAG. CoE unifies Chain-of-Thought (CoT) reasoning and visual evidence attribution by grounding reference elements in reasoning steps to specific regions with bounding boxes and page indexes. To enable VLMs to generate such evidence-grounded reasoning, we propose Look As You Think (LAT), a reinforcement learning framework that trains models to produce verifiable reasoning paths with consistent attribution. During training, LAT evaluates the attribution consistency of each evidence region and provides rewards only when the CoE trajectory yields correct answers, encouraging process-level self-verification. Experiments on vanilla Qwen2.5-VL-7B-Instruct with Paper‑ and Wiki‑VISA benchmarks show that LAT consistently improves the vanilla model in both single- and multi-image settings, yielding average gains of 8.13\% in soft exact match (EM) and 48.4\% in IoU\@0.5. Meanwhile, LAT not only outperforms the supervised fine-tuning baseline, which is trained to directly produce answers with attribution, but also exhibits stronger generalization across domains.

Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning

Multi-modal Retrieval-Augmented Generation (MMRAG) enables highly credible generation by integrating external multi-modal knowledge, thus demonstrating impressive performance in complex multi-modal scenarios. However, existing MMRAG methods fail to clarify the reasoning logic behind retrieval and response generation, which limits the explainability of the results. To address this gap, we propose to introduce reinforcement learning into multi-modal retrieval-augmented generation, enhancing the reasoning capabilities of multi-modal large language models through a two-stage reinforcement fine-tuning framework to achieve explainable multi-modal retrieval-augmented generation. Specifically, in the first stage, rule-based reinforcement fine-tuning is employed to perform coarse-grained point-wise ranking of multi-modal documents, effectively filtering out those that are significantly irrelevant. In the second stage, reasoning-based reinforcement fine-tuning is utilized to jointly optimize fine-grained list-wise ranking and answer generation, guiding multi-modal large language models to output explainable reasoning logic in the MMRAG process. Our method achieves state-of-the-art results on WebQA and MultimodalQA, two benchmark datasets for multi-modal retrieval-augmented generation, and its effectiveness is validated through comprehensive ablation experiments.

Content not yet available

Downloads

Next from AAAI 2026

LLaVA³: Representing 3D Scenes Like a Cubist Painter to Boost 3D Scene Understanding of VLMs

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2026

LLaVA³: Representing 3D Scenes Like a Cubist Painter to Boost 3D Scene Understanding of VLMs

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads