Shagufta Mehnaz
5 papers · 2024–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
Top co-authors
Research topics
Keywords
adversarial robustness
(2)
semantic similarity
(2)
large language model
(2)
chain-of-thought reasoning
(1)
machine unlearning
(1)
pre-trained language model
(1)
privacy leakage
(1)
prompt sensitivity
(1)
membership inference
(1)
jailbreak defense
(1)
software security
(1)
zero-shot performance
(1)
toxicity mitigation
(1)
adversarial text generation
(1)
data extraction attack
(1)
automated program repair
(1)
adversarial example attack
(1)
inference-time defense
(1)
reinforcement learning
(1)
logical vulnerability
(1)
Papers
Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models
AAAI 2026
LogicEval: A Systematic Framework for Evaluating Automated Repair Techniques for Logical Vulnerabilities in Real-World Software
ACL 2026
Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage
AAAI 2025
From Insight to Exploit: Leveraging LLM Collaboration for Adaptive Adversarial Text Generation
EMNLP 2025
Semantic-Preserving Adversarial Example Attack against BERT
NAACL 2024