6 papers
Agentic Adversarial Rewriting Exposes Architectural Vulnerabilities in Black-Box NLP Pipelines
Mazal Bethany, Kim-Kwang Raymond Choo, Nishant Vishwamitra +1
Multi-component natural language processing (NLP) pipelines are increasingly deployed for high-stakes decisions, yet no existing adversarial method can test their robustness under…
Reflective Agreement: Combining Self-Mixture of Agents with a Sequence Tagger for Robust Event Extraction
Fatemeh Haji, Mazal Bethany, Cho-Yu Jason Chiang +2
Event Extraction (EE) involves automatically identifying and extracting structured information about events from unstructured text, including triggers, event types, and arguments.…
CAMOUFLAGE: Exploiting Misinformation Detection Systems Through LLM-driven Adversarial Claim Transformation
Mazal Bethany, Nishant Vishwamitra, Cho-Yu Jason Chiang +1
Automated evidence-based misinformation detection systems, which evaluate the veracity of short claims against evidence, lack comprehensive analysis of their adversarial vulnerabil…
Lateral Phishing With Large Language Models: A Large Organization Comparative Study
Mazal Bethany, Athanasios Galiopoulos, Emet Bethany +4
The emergence of Large Language Models (LLMs) has heightened the threat of phishing emails by enabling the generation of highly targeted, personalized, and automated attacks. Tradi…
Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent
Fatemeh Haji, Mazal Bethany, Maryam Tabar +3
Multi-agent strategies have emerged as a promising approach to enhance the reasoning abilities of Large Language Models (LLMs) by assigning specialized roles in the problem-solving…
Jailbreaking Large Language Models with Symbolic Mathematics
Emet Bethany, Mazal Bethany, Juan Arturo Nolazco Flores +2
Recent advancements in AI safety have led to increased efforts in training and red-teaming large language models (LLMs) to mitigate unsafe content generation. However, these safety…