• Publications
  • Influence
Privacy-Aware Recommendation with Private-Attribute Protection using Adversarial Learning
TLDR
This work is the first attempt to build a Recommendation with Attribute Protection (RAP) model which simultaneously recommends relevant items and counters private-attribute inference attacks.
Deep Reinforcement Learning-based Text Anonymization against Private-Attribute Inference
TLDR
A novel Reinforcement Learning-based Text Anonymizor, RLTA, which addresses the problem of private-attribute leakage while preserving the utility of textual data and shows the effectiveness in preserving both privacy and utility.
ParsiNLU: A Suite of Language Understanding Challenges for Persian
TLDR
This work introduces ParsiNLU, the first benchmark in Persian language that includes a range of language understanding tasks—reading comprehension, textual entailment, and so on, and presents the first results on state-of-the-art monolingual and multilingual pre-trained language models on this benchmark and compares them with human performance.
Mitigating Bias in Session-based Cyberbullying Detection: A Non-Compromising Approach
TLDR
A context-aware and model-agnostic debiasing strategy that leverages a reinforcement learning technique, without requiring any extra resources or annotations apart from a pre-defined set of sensitive triggers commonly used for identifying cyberbullying instances is proposed.
Causal Learning for Socially Responsible AI
TLDR
A survey of state-of-the-art methods of causal learning for SRAI, examining the seven CL tools to enhance the social responsibility of AI and reviewing how existing works have succeeded using these tools to tackle issues in developing SRAi such as fairness.
Topic-Preserving Synthetic News Generation: An Adversarial Deep Reinforcement Learning Approach
TLDR
This paper proposes a novel deep reinforcement learning-based method to control the output of GPT-2 with respect to a given news topic and considers realistic news as news that cannot be easily detected by a fake news classifier.
"Let's Eat Grandma": When Punctuation Matters in Sentence Representation for Sentiment Analysis
TLDR
It is hypothesized that punctuation could play a significant role in sentiment analysis and a novel representation model to improve syntactic and contextual performance is proposed and corroborated by conducting experiments on publicly available datasets.
Decision Deferral in a Human-AI Joint Face-Matching Task: Effects on Human Performance and Trust
This study investigates how human performance and trust are affected by the decision deferral rates of an AI-enabled decision support system in a high criticality domain such as security screening,
Toward Privacy and Utility Preserving Image Representation
TLDR
This paper proposes a principled framework called the Adversarial Image Anonymizer (AIA), which first creates an image representation using a generative model, then enhances the learned image representations using adversarial learning to preserve privacy and utility for a given task.
Domain Adaptive Fake News Detection via Reinforcement Learning
TLDR
This work addresses the limitations of existing automated fake news detection models by incorporating auxiliary information into a novel reinforcement learning-based model called REinforced Adaptive Learning Fake News Detection (REAL-FND), which exploits cross-domain and within-domain knowledge that makes it robust in a target domain, despite being trained in a different source domain.
...
...