Image de couverture de livre

Scanning Trojaned Models Using Out-of-Distribution Samples

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mirzaei, Hossein, Ansari, Ali, Nia, Bahar Dibaei, Nafez, Mojtaba, Madadi, Moein, Rezaee, Sepehr, Taghavi, Zeinab Sadat, Maleki, Arad, Shamsaie, Kian, Hajialilue, Mahdi, Habibi, Jafar, Sabokrou, Mohammad, Rohban, Mohammad Hossein
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Contrastive Teacher-Student Framework for Novelty Detection under Style Shifts
par: Mirzaei, Hossein, et autres
Publié: (2025)

Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection
par: Mirzaei, Hossein, et autres
Publié: (2025)

PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomalies
par: Nafez, Mojtaba, et autres
Publié: (2025)

DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion
par: Mirzaei, Hossein, et autres
Publié: (2025)

Universal Novelty Detection Through Adaptive Contrastive Learning
par: Mirzaei, Hossein, et autres
Publié: (2024)

Killing it with Zero-Shot: Adversarially Robust Novelty Detection
par: Mirzaei, Hossein, et autres
Publié: (2025)

Backdooring Outlier Detection Methods: A Novel Attack Approach
par: Taghavi, ZeinabSadat, et autres
Publié: (2024)

FrameShield: Adversarially Robust Video Anomaly Detection
par: Nafez, Mojtaba, et autres
Publié: (2025)

Leveraging Graph-RAG and Prompt Engineering to Enhance LLM-Based Automated Requirement Traceability and Compliance Checks
par: Masoudifard, Arsalan, et autres
Publié: (2024)

Towards an Explainable Comparison and Alignment of Feature Embeddings
par: Jalali, Mohammad, et autres
Publié: (2025)

When Exploration Comes for Free with Mixture-Greedy: Do we need UCB in Diversity-Aware Multi-Armed Bandits?
par: Nia, Bahar Dibaei, et autres
Publié: (2026)

Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay
par: Rezaei, Hossein, et autres
Publié: (2024)

Real-Time Knee Angle Prediction Using EMG and Kinematic Data with an Attention-Based CNN-LSTM Network and Transfer Learning Across Multiple Datasets
par: Mollahossein, Mojtaba, et autres
Publié: (2025)

What Are We Really Measuring? Rethinking Dataset Bias in Web-Scale Natural Image Collections via Unsupervised Semantic Clustering
par: Saleknia, Amir Hossein, et autres
Publié: (2026)

Attention-Based Convolutional Neural Network Model for Human Lower Limb Activity Recognition using sEMG
par: Mollahossein, Mojtaba, et autres
Publié: (2025)

Hallucination as an Upper Bound: A New Perspective on Text-to-Image Evaluation
par: Kasaei, Seyed Amir, et autres
Publié: (2025)

RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples
par: Mirzaei, Hossein, et autres
Publié: (2025)

A novel optimization‐based modal pushover analysis procedure for estimating the response of structures
par: Moein Mirzaei, et autres
Publié: (2024)

Toward IIT-Inspired Consciousness in LLMs: A Reward-Based Learning Framework
par: Akbari, Hamid Reza, et autres
Publié: (2026)

Non-Gaussianity consistency relations and their consequences for the peaks
par: Namjoo, Mohammad Hossein, et autres
Publié: (2024)

Geometry of non-Gaussianity in transient non-attractor inflation
par: Namjoo, Mohammad Hossein, et autres
Publié: (2025)

Modulation and Coding for NOMA and RSMA
par: Jafarkhani, Hamid, et autres
Publié: (2024)

Resources of the advantage in quantum Illumination: Discord and entanglement
par: Asadollahi, Mojtaba, et autres
Publié: (2026)

The Silent Judge: Unacknowledged Shortcut Bias in LLM-as-a-Judge
par: Marioriyad, Arash, et autres
Publié: (2025)

Generalization and Membership Inference Attack a Practical Perspective
par: Rahmani, Fateme, et autres
Publié: (2026)

Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models
par: Abbasi, Reza, et autres
Publié: (2024)

Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP
par: Abbasi, Reza, et autres
Publié: (2024)

All Centers Are at most a Few Tokens Apart: Knowledge Distillation with Domain Invariant Prompt Tuning
par: Ezzati, Amir Mohammad, et autres
Publié: (2025)

Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs
par: Salimi, Moein, et autres
Publié: (2026)

SORA: Free Second-Order Attacks in Fast Adversarial Training
par: Teymourian, Mazdak, et autres
Publié: (2026)

Novel Pipeline for Diagnosing Acute Lymphoblastic Leukemia Sensitive to Related Biomarkers
par: Farsangi, Amirhossein Askari, et autres
Publié: (2023)

Accent-Invariant Automatic Speech Recognition via Saliency-Driven Spectrogram Masking
par: Sameti, Mohammad Hossein, et autres
Publié: (2025)

Investigating the Physicochemical and Antioxidant Properties of Goat Milk Enriched With Rice Extract Fermented by Exopolysaccharide‐Producing Lactic Bacteria for Functional Yogurt Production
par: Mohammad Hossein Maleki, et autres
Publié: (2025)

Snuffy: Efficient Whole Slide Image Classifier
par: Jafarinia, Hossein, et autres
Publié: (2024)

CRISPR: Ensemble Model
par: Rostami, Mohammad, et autres
Publié: (2024)

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models
par: Rezaei, Parham, et autres
Publié: (2025)

Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models
par: Marioriyad, Arash, et autres
Publié: (2024)

Lying to Win: Assessing LLM Deception through Human-AI Games and Parallel-World Probing
par: Marioriyad, Arash, et autres
Publié: (2026)

Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training
par: Salimi, Moein, et autres
Publié: (2026)

No Concept Left Behind: Test-Time Optimization for Compositional Text-to-Image Generation
par: Sameti, Mohammad Hossein, et autres
Publié: (2025)