Canada

Image segmentation is foundational to computer vision applications, and the Segment Anything Model (SAM) has become a leading base model for these tasks. However, SAM falters in specialized downstream challenges, leading to various customized SAM models. We introduce BadSAM, a backdoor attack tailored for SAM, revealing that customized models can harbor malicious behaviors. Using the CAMO dataset, we confirm BadSAM&#39;s efficacy and identify SAM vulnerabilities. This study paves the way for the development of more secure and customizable vision foundation models.

AAAI 2024

BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract)

peai: privacy and security

robustness & trustworthiness

peai: safety

cv: segmentation

Image segmentation is foundational to computer vision applications, and the Segment Anything Model (SAM) has become a leading base model for these tasks. However, SAM falters in specialized downstream challenges, leading to various customized SAM models. We introduce BadSAM, a backdoor attack tailored for SAM, revealing that customized models can harbor malicious behaviors. Using the CAMO dataset, we confirm BadSAM's efficacy and identify SAM vulnerabilities. This study paves the way for the development of more secure and customizable vision foundation models.

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

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-24 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.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

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. 

Gaze estimation is an important research area in computer vision and machine learning. Eye-tracking and gaze-based interactions have made assistive technology (AT) more accessible to people with physical limitations. However, a non-negligible proportion of existing AT users, including those having dyskinetic cerebral palsy (CP) or severe intellectual disabilities (ID), have difficulties in using eye trackers due to their involuntary body movements. In this paper, we propose an adaptation method pertaining to head movement prediction and fixation smoothing to stabilize our target users' gaze points on the screen and improve their user experience (UX) in gaze-based interaction. Our empirical experimentation shows that our method significantly shortens the users' selection time and increases their selection accuracy.

Gaze-Based Interaction Adaptation for People with Involuntary Head Movements (Student Abstract)

As Large Language Models (LLMs) become more prevalent in various fields, it is crucial to rigorously assess the quality of their explanations. Our research introduces a task-agnostic framework for evaluating free-text rationales, drawing on insights from both linguistics and machine learning. We evaluate two dimensions of explainability: fidelity and interpretability. For fidelity, we propose methods suitable for proprietary LLMs where direct introspection of internal features is unattainable. For interpretability, we use language models instead of human evaluators, addressing concerns about subjectivity and scalability in evaluations. We apply our framework to evaluate GPT-3.5 and the impact of prompts on the quality of its explanations. In conclusion, our framework streamlines the evaluation of explanations from LLMs, promoting the development of safer models.

Automated Assessment of Fidelity and Interpretability: An Evaluation Framework for Large Language Models’ Explanations (Student Abstract)

The performance of artificial neural networks (ANNs) degrades when training data are limited or imbalanced. In contrast, the human brain can learn quickly from just a few examples. Here, we investigated the role of sleep in improving the performance of ANNs trained with limited data on the MNIST and Fashion MNIST datasets. Sleep was implemented as an unsupervised phase with local Hebbian type learning rules. We found a significant boost in accuracy after the sleep phase for models trained with limited data in the range of 0.5-10% of total MNIST or Fashion MNIST datasets. When more than 10% of the total data was used, sleep alone had a slight negative impact on performance, but this was remedied by fine-tuning on the original data. This study sheds light on a potential synaptic weight dynamics strategy employed by the brain during sleep to enhance memory performance when training data are limited or imbalanced.

Sleep-Like Unsupervised Replay Improves Performance When Data Are Limited or Unbalanced (Student Abstract) | VIDEO

As data privacy issues grow, finding the best privacy preservation algorithm for each situation is increasingly essential. This research has focused on understanding the frequency oracles (FO) privacy preservation algorithms. FO conduct the frequency estimation of any value in the domain. The aim is to explore how each can be best used and recommend which one to use with which data type. We experimented with different data scenarios and federated learning settings. Results showed clear guidance on when to use a specific algorithm.

Frequency Oracle for Sensitive Data Monitoring (Student Abstract)

Face video stylization aims to convert real face videos into specified reference styles. While one-shot methods perform well in single-image stylization, ensuring continuity between frames and retaining the original facial expressions present challenges in video stylization. To address these issues, our approach employs a personalized diffusion model with pixel-level control. We propose Local Consistency Guidance(LCG) strategy, composed of local-cross attention and local style transfer, to ensure temporal consistency. This framework enables the synthesis of high-quality stylized face videos with excellent temporal continuity.

Local Consistency Guidance: Personalized Stylization Method of Face Video (Student Abstract)

Cross-domain Graph Meta-learning (CGML) has shown its promise, where meta-knowledge is extracted from few-shot graph data in multiple relevant but distinct domains. However, several recent efforts assume target data available, which commonly does not established in practice. In this paper, we devise a novel Cross-domain Data Augmentation for Graph Meta-Learning (CDA-GML), which incorporates the superiorities of CGML and Data Augmentation， has addressed intractable shortcomings of label sparsity, domain shift, and the absence of target data simultaneously. Specifically, our method simulates instance-level and task-level domain shift to alleviate the cross-domain generalization issue in conventional graph meta-learning. Experiments show that our method outperforms the existing state-of-the-art methods.

When Sparse Graph Representation Learning Falls into Domain Shift: Data Augmentation for Cross-Domain Graph Meta-Learning (Student Abstract)

In the last years, several variants of transformers have emerged. In this paper, we compare different transformer-based models for solving the reverse dictionary task and explore their use in the context of a serious game called The Dictionary Game.

Towards a Transformer-Based Reverse Dictionary Model for Quality Estimation of Definitions (Student Abstract) | VIDEO

Entity Resolution (ER) is the problem of algorithmically matching records, mentions, or entries that refer to the same underlying real-world entity. Traditionally, the problem assumes (at most) two datasets, between which records need to be matched. There is considerably less research in ER when k > 2 datasets are involved. The evaluation of such multipartite ER (M-ER) is especially complex, since the usual ER metrics assume (whether implicitly or explicitly) k < 3. This paper takes the first step towards motivating a k-tuple approach for evaluating M-ER. Using standard algorithms and k-tuple versions of metrics like precision and recall, our preliminary results suggest a significant difference compared to aggregated pairwise evaluation, which would first decompose the M-ER problem into independent bipartite problems and then aggregate their metrics. Hence, M-ER may be more challenging and warrant more novel approaches than current decomposition-based pairwise approaches would suggest.

Multipartite Entity Resolution: Motivating a K-Tuple Perspective (Student Abstract)

It is necessary to explore an effective point cloud completion mechanism that is of great significance for real-world tasks such as autonomous driving, robotics applications, and multi-target tracking. In this paper, we propose a point cloud completion method using a self-supervised transformer model based on the contextual constraints of scene flow. Our method uses the multi-frame point cloud context relationship as a guide to generate a series of token proposals, this priori condition ensures the stability of the point cloud completion. The experimental results show that the method proposed in this paper achieves high accuracy and good stability.

Scene Flow Prior Based Point Cloud Completion with Masked Transformer (Student Abstract)

Hashing-based recommendation (HR) methods, whose core idea is mapping users and items into hamming space, are common practice to improve item retrieval efficiency. However, existing HR fails to align optimization objective (i.e., Bayesian Personalized Ranking) and evaluation metric (i.e., Recall), leading to suboptimal performance. In this paper, we propose a smooth recall loss (termed as SRLoss), which targets Recall as the optimization objective. Due to the existence of discrete constraints, the optimization problem is NP-hard. To this end, we propose an approximation-adjustable gradient estimator to solve our problem. Experimental Results demonstrate the effectiveness of our proposed method.

Content not yet available

BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract)

Downloads

Next from AAAI 2024

Gaze-Based Interaction Adaptation for People with Involuntary Head Movements (Student Abstract)

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract)

.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 2024

Gaze-Based Interaction Adaptation for People with Involuntary Head Movements (Student Abstract)

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads