Cover Image

Agentic Adversarial Rewriting Exposes Architectural Vulnerabilities in Black-Box NLP Pipelines

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bethany, Mazal, Choo, Kim-Kwang Raymond, Vishwamitra, Nishant, Najafirad, Peyman
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually
by: Bethany, Mazal, et al.
Published: (2024)

CAMOUFLAGE: Exploiting Misinformation Detection Systems Through LLM-driven Adversarial Claim Transformation
by: Bethany, Mazal, et al.
Published: (2025)

Can Reinforcement Learning Unlock the Hidden Dangers in Aligned Large Language Models?
by: Karkevandi, Mohammad Bahrami, et al.
Published: (2024)

Deciphering Textual Authenticity: A Generalized Strategy through the Lens of Large Language Semantics for Detecting Human vs. Machine-Generated Text
by: Bethany, Mazal, et al.
Published: (2024)

Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent
by: Haji, Fatemeh, et al.
Published: (2024)

Reflective Agreement: Combining Self-Mixture of Agents with a Sequence Tagger for Robust Event Extraction
by: Haji, Fatemeh, et al.
Published: (2025)

Jailbreaking Large Language Models with Symbolic Mathematics
by: Bethany, Emet, et al.
Published: (2024)

Lateral Phishing With Large Language Models: A Large Organization Comparative Study
by: Bethany, Mazal, et al.
Published: (2024)

Enhancing Event Reasoning in Large Language Models through Instruction Fine-Tuning with Semantic Causal Graphs
by: Bethany, Mazal, et al.
Published: (2024)

Code Security Vulnerability Repair Using Reinforcement Learning with Large Language Models
by: Islam, Nafis Tanveer, et al.
Published: (2024)

Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis
by: Haji, Fatemeh, et al.
Published: (2026)

Vulnerability Disclosure through Adaptive Black-Box Adversarial Attacks on NIDS
by: Ennaji, Sabrine, et al.
Published: (2025)

Enhancing Reverse Engineering: Investigating and Benchmarking Large Language Models for Vulnerability Analysis in Decompiled Binaries
by: Manuel, Dylan, et al.
Published: (2024)

Unintentional Security Flaws in Code: Automated Defense via Root Cause Analysis
by: Islam, Nafis Tanveer, et al.
Published: (2024)

An Unbiased Transformer Source Code Learning with Semantic Vulnerability Graph
by: Islam, Nafis Tanveer, et al.
Published: (2023)

Feature-Selective Representation Misdirection for Machine Unlearning
by: Chen, Taozhao, et al.
Published: (2025)

Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization
by: Liu, Shiyan, et al.
Published: (2026)

Exposing LLM Vulnerabilities: Adversarial Scam Detection and Performance
by: Chang, Chen-Wei, et al.
Published: (2024)

LLM-Powered Code Vulnerability Repair with Reinforcement Learning and Semantic Reward
by: Islam, Nafis Tanveer, et al.
Published: (2024)

AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing
by: Nunez, Ana, et al.
Published: (2024)

Beyond the Black Box: Interpretability of Agentic AI Tool Use
by: Tatsat, Hariom, et al.
Published: (2026)

Enhancing Source Code Security with LLMs: Demystifying The Challenges and Generating Reliable Repairs
by: Islam, Nafis Tanveer, et al.
Published: (2024)

Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software
by: Kordonsky, Tomer, et al.
Published: (2026)

Beyond Black-Box Labels: Interpretable Criteria for Diagnosing Subjective NLP Tasks
by: Rair, Nisrine, et al.
Published: (2026)

No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal Discovery
by: Han, Xiaoxue, et al.
Published: (2025)

Beyond Black-Box Benchmarking: Observability, Analytics, and Optimization of Agentic Systems
by: Moshkovich, Dany, et al.
Published: (2025)

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
by: Domico, Kyle, et al.
Published: (2025)

`Do as I say not as I do': A Semi-Automated Approach for Jailbreak Prompt Attack against Multimodal LLMs
by: Chiu, Chun Wai, et al.
Published: (2025)

Rewriting the Budget: A General Framework for Black-Box Attacks Under Cost Asymmetry
by: Salmani, Mahdi, et al.
Published: (2025)

A Blockchain-Monitored Agentic AI Architecture for Trusted Perception-Reasoning-Action Pipelines
by: Jan, Salman, et al.
Published: (2025)

DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing
by: Shankar, Shreya, et al.
Published: (2024)

Are You Human? An Adversarial Benchmark to Expose LLMs
by: Gressel, Gilad, et al.
Published: (2024)

Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations
by: Manna, Supriya, et al.
Published: (2024)

Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving
by: Wang, Lu, et al.
Published: (2025)

Beyond the Black Box: A Cognitive Architecture for Explainable and Aligned AI
by: Keyi, Hu
Published: (2025)

Contract And Conquer: How to Provably Compute Adversarial Examples for a Black-Box Model?
by: Chistyakova, Anna, et al.
Published: (2026)

How stealthy is stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real World
by: Panebianco, Francesco, et al.
Published: (2025)

DARWIN: Dynamic Agentically Rewriting Self-Improving Network
by: Jiang, Henry
Published: (2026)

AutoEG: Exploiting Known Third-Party Vulnerabilities in Black-Box Web Applications
by: Yang, Ruozhao, et al.
Published: (2026)

EASTER: Embedding Aggregation-based Heterogeneous Models Training in Vertical Federated Learning
by: Wang, Shuo, et al.
Published: (2023)