Papers by Maha Tufail Agro
TrojanWave: Exploiting Prompt Learning for Stealthy Backdoor Attacks on Large Audio-Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that ALMs are vulnerable to adversarial attacks. |
| Approach: | They propose a backdoor attack tailored to the prompt-learning setting in frozen audio-language models. |
| Outcome: | The proposed method injects backdoors solely through learnable prompts, making it highly scalable and effective in few-shot settings. |
Profiling News Media for Factuality and Bias Using LLMs and the Fact-Checking Methodology of Human Experts (2025.findings-acl)
Copied to clipboard
| Challenge: | Important efforts to characterize news media outlets in terms of their political bias and factuality are labor-intensive and prone to human biases. |
| Approach: | They propose a method that emulates criteria used by professional fact-checkers to assess the factuality and political bias of an entire outlet. |
| Outcome: | The proposed method improves on baselines and with multiple LLMs. |