14 papers
Breaking Adversarial Transferability in Fine-Tuned Speech Recognition
Mojtaba Nafez, Aref Mousavi, Mohammad Ebrahim Mahdavi +3
Many organizations fine-tune publicly available pretrained Automatic Speech Recognition (ASR) models and deploy them in black-box settings, assuming limited access provides protect…
Transferable Adversarial Robustness for Speech Foundation Models via Hierarchical Stabilization
Aref Mousavi, Shahab Sherafat, Kiarash Kiani Feriz +4
Frozen speech foundation models (SFMs) make downstream adaptation efficient: the backbone can stay fixed while a task learns layer fusion and a lightweight classifier. Full adversa…
Learning Transferable Skills using Goal-Conditioned Bisimulation
Mohammad Amin Abbasfar, Farbod Azimmohseni, Mohammad Hossein Rohban
Unsupervised skill discovery has emerged as a promising approach for leveraging reward-free datasets to pretrain general-purpose policies. However, current skill discovery methods…
Weeding Out Bad Seeds: Initial-Noise-Robust Unlearning for Text-to-Image Diffusion Models
Arian Komaei Koma, Seyed Amir Kasaei, Aida Aryafar +6
Machine unlearning has emerged as a critical post-hoc safety measure to erase sensitive concepts from Text-to-Image (T2I) models without prohibitive retraining. However, we reveal…
CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs
Moein Salimi, Danial Parnian, Shaygan Adim +6
Abductive reasoning, often characterized as inference to the best explanation, is central to explanation under uncertainty, from everyday sense-making and investigation to scientif…
KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation
Farbod Davoodi, Seyed Reza Tavakoli Shiyadeh, Pooria Safaei +12
Text-to-Image (TTI) systems are now everyday infrastructure for journalism, education, advertising, and public communication, and the demographic and cultural stereotypes they inhe…
SORA: Free Second-Order Attacks in Fast Adversarial Training
Mazdak Teymourian, Ramtin Moslemi, Farzan Rahmani +1
Adversarial Training (AT) is a leading defense against adversarial examples but often suffers from Catastrophic Overfitting (CO) in efficient single-step variants, where robustness…
Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models
Arian Komaei Koma, Seyed Amir Kasaei, AmirMahdi Sadeghzadeh +1
Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been introduced to make the model…
Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs
Moein Salimi, Shaygan Adim, Danial Parnian +3
Regardless of its foundational role in human discovery and sense-making, abductive reasoning--the inference of the most plausible explanation for an observation--has been relativel…
Generalization and Membership Inference Attack a Practical Perspective
Fateme Rahmani, Mahdi Jafari Siavoshani, Mohammad Hossein Rohban
With the emergence of new evaluation metrics and attack methodologies for Membership Inference Attacks (MIA), it becomes essential to reevaluate previously accepted assumptions. In…
Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training
Moein Salimi, Babak Hosseini Mohtasham, Amin Aghakasiri +6
Large Language Models (LLMs) have demonstrated potential in automating scientific ideation, yet current approaches relying on iterative prompting or complex multi-agent architectur…
Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models
Arian Komaei Koma, Seyed Amir Kasaei, Ali Aghayari +2
Post-hoc unlearning has emerged as a practical mechanism for removing undesirable concepts from large text-to-image diffusion models. However, prior work primarily evaluates unlear…
Hidden Meanings in Plain Sight: RebusBench for Evaluating Cognitive Visual Reasoning
Seyed Amir Kasaei, Arash Marioriyad, Mahbod Khaleti +3
Large Vision-Language Models (LVLMs) have achieved remarkable proficiency in explicit visual recognition, effectively describing what is directly visible in an image. However, a cr…
Lying to Win: Assessing LLM Deception through Human-AI Games and Parallel-World Probing
Arash Marioriyad, Ali Nouri, Mohammad Hossein Rohban +1
As Large Language Models (LLMs) transition into autonomous agentic roles, the risk of deception-defined behaviorally as the systematic provision of false information to satisfy ext…