Cover Image

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sinha, Yash, Baser, Manit, Mandal, Murari, Divakaran, Dinil Mon, Kankanhalli, Mohan
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multimodal Large Language Models for Phishing Webpage Detection and Identification
by: Lee, Jehyun, et al.
Published: (2024)

AI-based Traffic Modeling for Network Security and Privacy: Challenges Ahead
by: Divakaran, Dinil Mon
Published: (2025)

Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
by: Nawal, Aditya, et al.
Published: (2026)

MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study
by: Van hamme, Tim, et al.
Published: (2026)

ThinkEval: Practical Evaluation of Knowledge Leakage in LLM Editing using Thought-based Knowledge Graphs
by: Baser, Manit, et al.
Published: (2025)

From ML to LLM: Evaluating the Robustness of Phishing Webpage Detection Models against Adversarial Attacks
by: Kulkarni, Aditya, et al.
Published: (2024)

UniNet: A Unified Multi-granular Traffic Modeling Framework for Network Security
by: Wu, Binghui, et al.
Published: (2025)

Involuntary Jailbreak: On Self-Prompting Attacks
by: Guo, Yangyang, et al.
Published: (2025)

RECTor: Robust and Efficient Correlation Attack on Tor
by: Wu, Binghui, et al.
Published: (2025)

LLMs for Cyber Security: New Opportunities
by: Divakaran, Dinil Mon, et al.
Published: (2024)

UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs
by: Sinha, Yash, et al.
Published: (2024)

Mitigating Bias in Machine Learning Models for Phishing Webpage Detection
by: Kulkarni, Aditya, et al.
Published: (2024)

ZEST: Attention-based Zero-Shot Learning for Unseen IoT Device Classification
by: Wu, Binghui, et al.
Published: (2023)

Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Review
by: Allana, Sonal, et al.
Published: (2025)

When Reject Turns into Accept: Quantifying the Vulnerability of LLM-Based Scientific Reviewers to Indirect Prompt Injection
by: Sahoo, Devanshu, et al.
Published: (2025)

"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
by: Wang, Libo
Published: (2024)

AttacKG+:Boosting Attack Knowledge Graph Construction with Large Language Models
by: Zhang, Yongheng, et al.
Published: (2024)

CLaRE-ty Amid Chaos: Quantifying Representational Entanglement to Predict Ripple Effects in LLM Editing
by: Baser, Manit, et al.
Published: (2026)

BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
by: Liu, Shuaitong, et al.
Published: (2025)

Conflicts Make Large Reasoning Models Vulnerable to Attacks
by: Liu, Honghao, et al.
Published: (2026)

EagleEye: Attention to Unveil Malicious Event Sequences from Provenance Graphs
by: Gysel, Philipp, et al.
Published: (2024)

FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts
by: Gong, Yichen, et al.
Published: (2023)

A Survey of Attacks on Large Language Models
by: Xu, Wenrui, et al.
Published: (2025)

Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
by: Tu, Shangqing, et al.
Published: (2024)

Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
by: Truong, Vu Tuan, et al.
Published: (2026)

Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models
by: Wang, Shuqiang, et al.
Published: (2026)

ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models
by: Liu, Xiaogeng, et al.
Published: (2026)

Membership Inference Attacks on Tokenizers of Large Language Models
by: Tong, Meng, et al.
Published: (2025)

A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
by: Li, Jie, et al.
Published: (2024)

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models
by: Park, Junyoung, et al.
Published: (2026)

Recent Advances in Attack and Defense Approaches of Large Language Models
by: Cui, Jing, et al.
Published: (2024)

Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models
by: Li, Xi, et al.
Published: (2024)

TensorCommitments: A Lightweight Verifiable Inference for Language Models
by: Baser, Oguzhan, et al.
Published: (2026)

Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey
by: Jain, Bhavuk, et al.
Published: (2026)

SoK: Robustness in Large Language Models against Jailbreak Attacks
by: Xu, Feiyue, et al.
Published: (2026)

Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models
by: Das, Badhan Chandra, et al.
Published: (2026)

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
by: Ying, Zonghao, et al.
Published: (2025)

Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
by: Luo, Weidi, et al.
Published: (2025)

Hiding in Plain Sight: Detectability-Aware Antidistillation of Reasoning Models
by: Hartman, Max, et al.
Published: (2026)

Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models
by: Yang, Fan
Published: (2025)