Singapore

Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack strategies still leave persistent traces that may be detected through static analysis. In this work, we introduce the first paradigm of revocable backdoor attacks, where the backdoor can be proactively and thoroughly removed after the attack objective is achieved. We formulate the trigger optimization in revocable backdoor attacks as a bilevel optimization problem: by simulating both backdoor injection and unlearning processes, the trigger generator is optimized to achieve a high attack success rate (ASR) while ensuring that the backdoor can be easily erased through unlearning. To mitigate the optimization conflict between injection and removal objectives, we employ a deterministic partition of poisoning and unlearning samples to reduce sampling-induced variance, and further apply the Projected Conflicting Gradient (PCGrad) technique to resolve the remaining gradient conflicts. Experiments on CIFAR-10 and ImageNet demonstrate that our method maintains ASR comparable to state-of-the-art backdoor attacks, while enabling effective removal of backdoor behavior after unlearning. This work opens a new direction for backdoor attack research and presents new challenges for the security of machine learning systems.

AAAI 2026

Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning

revocable backdoor attack;machine unlearning;bilevel optimization

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

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.

To access this event page, you need to log in with the **email address you registered with**. 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.

Written Multi-Party Conversations (WMPCs) are widely studied across disciplines, with social media as a primary data source due to their accessibility. However, these datasets raise privacy concerns and often reflect platform-specific properties.
For example, interactions between speakers may be limited due to rigid platform structures (e.g., threads, tree-like discussions), which yield overly simplistic interaction patterns (e.g., one-to-one ``reply-to'' links). This work explores the feasibility of generating synthetic WMPCs with instruction-tuned Large Language Models (LLMs) by providing deterministic constraints such as dialogue structure and participants’ stance. We investigate two complementary strategies of leveraging LLMs in this context: (i.) LLMs as WMPC generators, where we task the LLM to generate a whole WMPC at once and (ii.) LLMs as WMPC parties, where the LLM generates one turn of the conversation at a time (made of speaker, addressee and message), provided the conversation history. We next introduce an analytical framework to evaluate compliance with the constraints, content quality, and interaction complexity for both strategies. Finally, we assess the level of obtained WMPCs via human and LLM-as-a-judge evaluations. We find stark differences among LLMs, with only some being able to generate high-quality WMPCs. We also find that turn-by-turn generation yields better conformance to constraints and higher linguistic variability than generating WMPCs in one pass. Nonetheless, our structural and qualitative evaluation indicates that both generation strategies can yield high-quality WMPCs.

Don’t Stop the Multi-Party! On Generating Synthetic Written Multi-Party Conversations with Constraints

With the widespread adoption of multi-view data in numerous fields, multi-view unsupervised feature selection (MUFS) has made notable strides in both feature pruning and missing-view completion. Nonetheless, existing MUFS methods typically rely on centralized servers, which cannot meet real-world demands for privacy preservation and distributed learning, and they often suffer from suboptimal solution and weak convergence guarantees. To address these challenges, IMUFFS, an incomplete multi-view unsupervised federated feature selection via cooperative particle swarm optimization (CPSO) and tensor-aligned learning (TAL) is proposed. Specifically, each client executes CPSO-TAL at two stages: (i) an external optimization phase that involves a CPSO, inspired by the co-evolutionary mechanism of hybrid breeding optimization algorithm, performing a global search in the feature space, and (ii) an internal optimization phase that leverages TAL with imputation and CP decomposition, where CP decomposition reduces dimensionality by decomposing the original tensor into a sum of core components, to learn low-dimensional embeddings, while simultaneously updating anchor graphs and view preference weights, thereby harmonizing imputation and representation learning. On the server side, a federated aggregation strategy using adaptive normalized mutual information (NMI) weighting combines the locally optimized feature selection (FS) weights and NMI scores from clients, ensuring privacy while improving the quality of FS and convergence. Extensive experiments on multiple datasets demonstrate that IMUFFS consistently outperforms state-of-the-art methods, yielding more effective and robust FS and enhancing better missing-view completion.

Incomplete Multi-View Unsupervised Federated Feature Selection via Cooperative Particle Swarm Optimization and Tensor-Aligned Learning

Modern AI services must continually adapt to newly joined domains, yet delivering high-quality customized models is hampered by label sparsity, domain shifts, and tight budgets. We formulate this challenge as the learning system expansion problem and introduce HaT, an efficient heterogeneity-aware knowledge-transfer framework. HaT first selects a small set of high-quality source models with minimal overhead, and then fuses their imperfect predictions through a sample-wise attention mixer. Later, it adaptively distills the fused knowledge into target models via a knowledge dictionary. Extensive experiments on different tasks and modalities show that HaT outperforms state-of-the-art baselines by up to 16.5\% accuracy, and saves 31.1\% training time and up to 93.0\% traffic.

Learning Systems Expansion with Efficient Heterogeneity-aware Knowledge Transfer

Promptable segmentation models such as SAM have established a powerful paradigm, enabling strong generalization to unseen objects and domains with minimal user input, including points, bounding boxes, and text prompts. Among these, bounding boxes stand out as particularly effective, often outperforming points while significantly reducing annotation costs. However, current training and evaluation protocols typically rely on synthetic prompts generated through simple heuristics, offering limited insight into real-world robustness. In this paper, we investigate the robustness of promptable segmentation models to natural variations in bounding box prompts. First, we conduct a controlled user study and collect thousands of real bounding box annotations. Our analysis reveals substantial variability in segmentation quality across users for the same model and instance, indicating that SAM-like models are highly sensitive to natural prompt noise. Then, since exhaustive testing of all possible user inputs is computationally prohibitive, we reformulate robustness evaluation as a white-box optimization problem over the bounding box prompt space. We introduce BREPS, a method for generating adversarial bounding boxes that minimize or maximize segmentation error while adhering to naturalness constraints. Finally, we benchmark state-of-the-art models across 10 datasets, spanning everyday scenes to medical imaging. All code and data will be released upon publication.

BREPS: Bounding-Box Robustness Evaluation of Promptable Segmentation

Visual impairment is a common condition worldwide, and cortical electrical stimulation is one of the approaches to aid in visual restoration. However, existing methods suffer from limited precision, flexibility, and generalization in generating the desired visual perception. In this paper, we propose a novel deep learning-based algorithm for cortical electrical stimulation, named ``MindSight," aimed at enhancing the clarity and accuracy of induced visual perceptions. Our framework introduces three key innovations: (1) A differentiable biophysical model simulating cortical state transitions under electrical stimulation, enabling end-to-end training; (2) A dual-path training architecture combining neural decoding fidelity with phosphene simulation constraints; (3) An attention-guided background gated network for input filtration and, a multi-channel activation constraint to ensure the effectiveness of electrical stimulation. We validated our approach through novel experiments with macaque monkeys, demonstrating superior performance in visual perception tasks. These results highlight the potential of our approach in assisting individuals with visual impairments.

MindSight: A Bio-Inspired Neural Architecture for Visual Restoration via Cortical Electrical Stimulation

Retrieval-Augmented Generation (RAG) has revolutionized Large Language Models' ability to access external knowledge, but current graph-based RAG approaches face critical limitations in managing hierarchical knowledge: they impose rigid compression quotas per layer that damage local graph structures, and they focus primarily on topological structure while neglecting semantic coherence. We introduce T-Retriever, a novel framework that reformulates attributed graph retrieval as tree-based retrieval using a semantic and structure guided encoding tree. Our approach integrates two key innovations: (1) Adaptive Compression Encoding, which eliminates artificial layer-specific compression quotas in favor of a global optimization strategy that preserves the graph's natural hierarchical organization, and (2) Semantic-Structural Entropy (S²-Entropy), which jointly optimizes for both topological cohesion and semantic consistency when creating hierarchical partitions. Extensive experiments across diverse graph reasoning benchmarks demonstrate that T-Retriever significantly outperforms state-of-the-art RAG methods.

T-Retriever: Tree-based Hierarchical Retrieval Augmented Generation for Textual Graphs

The surrogate gradient (SG) method has shown significant promise in enhancing the performance of deep spiking neural networks (SNNs), but it also introduces vulnerabilities to adversarial attacks. Although spike coding strategies and neural dynamics parameters have been extensively studied for their impact on robustness, the critical role of gradient magnitude, which reflects the model's sensitivity to input perturbations, remains underexplored. In SNNs, the gradient magnitude is primarily determined by the interaction between the membrane potential distribution (MPD) and the SG function. In this study, we investigate the relationship between the MPD and SG and its implications for improving the robustness of SNNs. Our theoretical analysis reveals that reducing the proportion of membrane potential lying within the gradient-available range of the SG function effectively mitigates the sensitivity of SNNs to input perturbations. Building upon this insight, we propose a novel MPD-driven surrogate gradient regularization (MPD-SGR) method, which enhances robustness by explicitly regularizing the MPD based on its interaction with the SG function. Extensive experiments across multiple image classification benchmarks and diverse network architectures confirm that the MPD-SGR method significantly enhances the resilience of SNNs to adversarial perturbations and exhibits strong generalizability across diverse network configurations, SG function variants, and spike encoding schemes.

MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularization

Recent advances in transformer-based text-to-motion generation have significantly improved motion quality. However, achieving both real-time performance and long-horizon scalability remains an open challenge. In this paper, we present MOGO (Motion Generation with One-pass), a novel autoregressive framework for efficient and scalable 3D human motion generation. MOGO consists of two key components. First, we introduce MoSA-VQ, a motion scale-adaptive residual vector quantization module that hierarchically discretizes motion sequences through learnable scaling parameters, which dynamically regulate the information flow at each layer to produce compact yet expressive multi-level representations. Second, to fully utilize the high-quality motion representations, we further design the RQHC-Transformer, a residual quantized hierarchical causal transformer that structurally aligns with the multi-level latent hierarchy produced by MoSA-VQ. Each level is decoded by a dedicated transformer block, enabling efficient multi-scale generation in a single forward pass. Compared to diffusion-based and LLM-based approaches, it achieves lower inference latency while maintaining high motion quality. Notably, our hierarchical latent modeling—through the synergy of MoSA-VQ and RQHC-Transformer—empowers MOGO with seamless and coherent infinite-length generation. By iteratively extending motion from any given frame and allowing control signals to be updated at arbitrary points, the model produces stable transitions and responds adaptively to new conditions, enabling real-time, controllable long-horizon synthesis with strong temporal consistency. Extensive experiments on HumanML3D and KIT-ML validate the quality and efficiency of our approach, while evaluation on the unseen CMP dataset demonstrates strong zero-shot generalization capabilities.

MOGO: Residual Quantized Hierarchical Causal Transformer for Real-Time and Infinite-Length 3D Human Motion Generation

Multimodal Large Language Models (MLLMs) have demonstrated impressive progress in single-image grounding and general multi-image understanding. Recently, some methods begin to address multi-image grounding. However, they are constrained by single-target localization and limited types of practical tasks, due to the lack of unified modeling for generalized grounding tasks.
Therefore, we propose GeM-VG, an MLLM capable of Generalized Multi-image Visual Grounding.
To support this, we systematically categorize and organize existing multi-image grounding tasks according to cognitive demands and introduce the MG-Data-240K dataset, addressing the limitations of existing datasets regarding target quantity and image relation.
To tackle the challenges of robustly handling diverse multi-image grounding tasks, we further propose a hybrid reinforcement finetuning strategy that integrates chain-of-thought (CoT) reasoning and direct answering, considering their complementary strengths.
This strategy adopts an R1-like algorithm guided by a carefully designed rule-based reward, effectively enhancing the model’s overall perception and reasoning capabilities.
Extensive experiments demonstrate the superior generalized grounding capabilities of our model. For multi-image grounding, it outperforms the previous leading MLLMs by 2.0\% and 9.7\% on MIG-Bench and MC-Bench, respectively. In single-image grounding, it achieves a 9.1\% improvement over the base model on ODINW. Furthermore, our model retains strong capabilities in general multi-image understanding.

GeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models

A 3D point cloud completion task is to generate completed 3D objects given partial observations. Auto-encoder-based models suffer from poor generalization ability to untrained 3D data. Current diffusion-based models add isotropic noise with the same variance in three $x, y, z$ axes. More importantly, these models ignore real-world anisotropic evolution properties of 3D particles from a non-equilibrium state to thermodynamic equilibrium in the real physical world due to the velocity and energy thermodynamics of the particles, leading to unstable completions of 3D object topology. This paper presents a novel physically-based anisotropic 3D diffusion model (3DDM) to address these issues. We also present derivations of our proposed forward and reverse processes and a loss function in closed form, thus reproducibility. The 3DDM contains anisotropic energy-aware forward and reverse processes with a novel anisotropic quadratic loss function. The forward process adds anisotropic 3D Gaussian noises per-axis and mimics the thermal non-equilibrium evolution towards Maxwellian equilibrium based on velocity and kinetic energy evolutions of 3D particles in the real physical space. The reverse process learns to denoise along per-axis and per-timestep anisotropically. The anisotropic quadratic loss function penalizes errors along certain axes, yielding a highly flexible and anisotropic reverse diffusion process and a physically realistic generative model. The 3DDM denoises along $x, y, z$ axes with different velocities from the non-equilibrium evolution, achieving fewer than 20 diffusion steps and strong generalization to unseen 3D objects and real-world scenes that were not trained.

Content not yet available

Next from AAAI 2026

Don’t Stop the Multi-Party! On Generating Synthetic Written Multi-Party Conversations with Constraints

Similar lecture

Forget the Unneeded: Backdooring Large Language Models via Contrastive-enhanced Machine Unlearning