SE
Sarah Erfani
cs.LGcs.CVcs.AIstat.MLcs.CRcs.CLcs.IRquant-phcs.ETcs.SD
On Valency
published · living versionsW_mje47hj7·v1 · currentpublished
Out-of-Distribution Detection in Continual Learning
with Nimeshika Udayangani, Flora D. Salim, Christopher Leckie
1 version
Preprints & journals
92 papers in the corpus · 2016–2026Out-of-Distribution Detection in Continual Learning2610.25901v1 · Nimeshika Udayangani, Flora D. Salim, Christopher Leckie et al.2026 · 0 citationsarXivon Valency
LLMs Learn to Evade Latent Monitors from Prior Feedback Alone2609.36490v1 · Hugo Lyons Keenan, Christopher Leckie, Sarah Erfani2026 · 0 citationsarXiv
VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation2609.35028v1 · Hanxun Huang, Yutao Wu, Qizhou Wang et al.2026 · 0 citationsarXiv
LAYERSCOPE: A Layerwise Characterization of Video and Multimodal Learned Representations2609.28086v2 · Sandra Arcos-Holzinger, Debashish Chakraborty, Rohita Mocharla et al.2026 · 0 citationsarXiv
VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs2608.30480v1 · Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie et al.2026 · 0 citationsarXiv
GeoDetect: Geometric Adversarial Detection for VLPs2607.14737v1 · Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie et al.2026 · 0 citationsarXiv
Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity2606.25343v3 · Heethanjan Kanagalingam, Thenukan Pathmanathan, Mokeeshan Vathanakumar et al.2026 · 0 citationsarXiv
Semantic Robustness Certification for Vision-Language Models2606.18839v1 · Peiyu Yang, Paul Montague, Feng Liu et al.2026 · 0 citationsarXiv
Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs2606.01710v1 · Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie et al.2026 · 0 citationsarXiv
TRACER: Persistent Regularization for Robust Multimodal Finetuning2605.29380v1 · Hesam Asadollahzadeh, Feng Liu, Christopher Leckie et al.2026 · 0 citationsarXiv
AudioMosaic: Contrastive Masked Audio Representation Learning2605.14231v1 · Hanxun Huang, Qizhou Wang, Xingjun Ma et al.2026 · 0 citationsarXiv
Fortifying Time Series: DTW-Certified Robust Anomaly Detection2605.07690v1 · Shijie Liu, Tansu Alpcan, Christopher Leckie et al.2026 · 0 citations39th Conference on Neural Information Processing Systems (NeurIPS 2025)
Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models2605.02715v1 · Sandra Arcos-Holzinger, Sarah M. Erfani, James Bailey et al.2026 · 0 citationsarXiv
Mechanistic Anomaly Detection via Functional Attribution2604.18970v2 · Hugo Lyons Keenan, Christopher Leckie, Sarah Erfani2026 · 0 citationsarXiv
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses2605.02900v2 · Xiao Li, Xiang Zheng, Yifeng Gao et al.2026 · 0 citationsarXiv
Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning2603.20662v1 · Xueqi Ma, Shuo Yang, Yanbei Jiang et al.2026 · 0 citationsarXiv
Semantic-aware Adversarial Fine-tuning for CLIP2602.12461v1 · Jiacheng Zhang, Jinhao Li, Hanxun Huang et al.2026 · 0 citationsarXiv
Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models2602.01025v1 · Kaiyuan Cui, Yige Li, Yutao Wu et al.2026 · 0 citationsarXiv
Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models2512.16244v2 · Xueqi Ma, Xingjun Ma, Sarah Monazam Erfani et al.2025 · 0 citationsarXiv
Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules2512.10300v1 · Yanbei Jiang, Xueqi Ma, Shu Liu et al.2025 · 0 citationsarXiv
On the Bayes Inconsistency of Disagreement Discrepancy Surrogates2512.05931v1 · Neil G. Marchant, Andrew C. Cullen, Feng Liu et al.2025 · 0 citationsarXiv
Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning2512.10978v1 · Xueqi Ma, Jun Wang, Yanbei Jiang et al.2025 · 1 citationarXiv
SupLID: Geometrical Guidance for Out-of-Distribution Detection in Semantic Segmentation2511.18816v1 · Nimeshika Udayangani, Sarah Erfani, Christopher Leckie2025 · 1 citationIn Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM 2025), pages 2905-2914, 2025
Exploiting Inter-Sample Information for Long-tailed Out-of-Distribution Detection2511.16015v1 · Nimeshika Udayangani, Hadi M. Dolatabadi, Sarah Erfani et al.2025 · 3 citationsIn 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (pp. 8546-8555). IEEE
Reasoning Like Experts: Leveraging Multimodal Large Language Models for Drawing-based Psychoanalysis2510.19451v1 · Xueqi Ma, Yanbei Jiang, Sarah Erfani et al.2025 · 0 citationsarXiv
Intention-aware Hierarchical Diffusion Model for Long-term Trajectory Anomaly Detection2509.17068v1 · Chen Wang, Sarah Erfani, Tansu Alpcan et al.2025 · 0 citationsarXiv
AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds2509.04345v2 · Qizhou Wang, Hanxun Huang, Guansong Pang et al.2025 · 1 citationarXiv
Position: Certified Robustness Does Not (Yet) Imply Model Security2506.13024v2 · Andrew C. Cullen, Paul Montague, Sarah M. Erfani et al.2025 · 0 citationsarXiv
Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning2505.20621v1 · Shijie Liu, Andrew C. Cullen, Paul Montague et al.2025 · 0 citationsarXiv
Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning2505.19532v2 · Shijie Liu, Andrew C. Cullen, Paul Montague et al.2025 · 0 citationsarXiv
X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP2505.05528v3 · Hanxun Huang, Sarah Erfani, Yige Li et al.2025 · 0 citationsarXiv
Geometry-Guided Adversarial Prompt Detection via Curvature and Local Intrinsic Dimension2503.03502v2 · Canaan Yung, Hanxun Huang, Christopher Leckie et al.2025 · 0 citationsarXiv
Intrinsic and Extrinsic Factor Disentanglement for Recommendation in Various Context Scenarios2503.03524v2 · Yixin Su, Wei Jiang, Fangquan Lin et al.2025 · 1 citationarXiv
HALO: Robust Out-of-Distribution Detection via Joint Optimisation2502.19755v1 · Hugo Lyons Keenan, Sarah Erfani, Christopher Leckie2025 · 2 citationsarXiv
Detecting Backdoor Samples in Contrastive Language Image Pretraining2502.01385v2 · Hanxun Huang, Sarah Erfani, Yige Li et al.2025 · 0 citationsarXiv
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety2502.05206v6 · Xingjun Ma, Yifeng Gao, Yixu Wang et al.2025 · 18 citationsarXiv
Efficient Neural Implicit Representation for 3D Human Reconstruction2410.17741v1 · Zexu Huang, Sarah Monazam Erfani, Siying Lu et al.2024 · 32 citationsPattern Recognition, Vol. 156, 2024, Article No. 110758
Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models2406.02915v1 · Jinhao Li, Haopeng Li, Sarah Erfani et al.2024 · 3 citationsarXiv
Round Trip Translation Defence against Large Language Model Jailbreaking Attacks2402.13517v2 · Canaan Yung, Hadi Mohaghegh Dolatabadi, Sarah Erfani et al.2024 · 2 citationsarXiv
Be Persistent: Towards a Unified Solution for Mitigating Shortcuts in Deep Learning2402.11237v2 · Hadi M. Dolatabadi, Sarah M. Erfani, Christopher Leckie2024 · 0 citationsarXiv
OIL-AD: An Anomaly Detection Framework for Sequential Decision Sequences2402.04567v1 · Chen Wang, Sarah Erfani, Tansu Alpcan et al.2024 · 1 citationarXiv
Unlearnable Examples For Time Series2402.02028v1 · Yujing Jiang, Xingjun Ma, Sarah Monazam Erfani et al.2024 · 2 citationsarXiv
LDReg: Local Dimensionality Regularized Self-Supervised Learning2401.10474v2 · Hanxun Huang, Ricardo J. G. B. Campello, Sarah Monazam Erfani et al.2024 · 0 citationsarXiv
End-to-End Anti-Backdoor Learning on Images and Time Series2401.03215v1 · Yujing Jiang, Xingjun Ma, Sarah Monazam Erfani et al.2024 · 0 citationsarXiv
It's Simplex! Disaggregating Measures to Improve Certified Robustness2309.11005v1 · Andrew C. Cullen, Paul Montague, Shijie Liu et al.2023 · 1 citationarXiv
Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks2308.07553v2 · Shijie Liu, Andrew C. Cullen, Paul Montague et al.2023 · 2 citationsProceedings of the 2023 AAAI Conference on Artificial Intelligence, 37(7), 8861-8869
Towards quantum enhanced adversarial robustness in machine learning2306.12688v1 · Maxwell T. West, Shu-Lok Tsang, Jia S. Low et al.2023 · 79 citationsNature Machine Intelligence 5, 581-589, 2023
The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Models2303.08500v2 · Hadi M. Dolatabadi, Sarah Erfani, Christopher Leckie2023 · 11 citationsarXiv
Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples2302.04379v4 · Andrew C. Cullen, Shijie Liu, Paul Montague et al.2023 · 1 citationarXiv
Distilling Cognitive Backdoor Patterns within an Image2301.10908v4 · Hanxun Huang, Xingjun Ma, Sarah Erfani et al.2023 · 13 citationsarXiv
Career total: 180 works. 92 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.