Cover Image

ShadowLogic: Backdoors in Any Whitebox LLM

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Schulz, Kasimir, Kawasaki, Amelia, Ring, Leo
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

ShadowGenes: Leveraging Recurring Patterns within Computational Graphs for Model Genealogy
by: Schulz, Kasimir, et al.
Published: (2025)

AutoBackdoor: Automating Backdoor Attacks via LLM Agents
by: Li, Yige, et al.
Published: (2025)

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations
by: Ge, Huaizhi, et al.
Published: (2024)

Exploring Backdoor Attack and Defense for LLM-empowered Recommendations
by: Ning, Liangbo, et al.
Published: (2025)

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
by: Bullwinkel, Blake, et al.
Published: (2026)

BadLLM-TG: A Backdoor Defender powered by LLM Trigger Generator
by: Zhang, Ruyi, et al.
Published: (2026)

TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
by: Mo, Xiaoxing, et al.
Published: (2025)

MARS: A Malignity-Aware Backdoor Defense in Federated Learning
by: Wan, Wei, et al.
Published: (2025)

BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
by: Yu, Haiyang, et al.
Published: (2024)

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
by: Yu, Miao, et al.
Published: (2025)

Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
by: Li, Yige, et al.
Published: (2026)

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward
by: Guo, Weiyang, et al.
Published: (2026)

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
by: Zhu, Pengyu, et al.
Published: (2025)

Unmasking the Shadows: Pinpoint the Implementations of Anti-Dynamic Analysis Techniques in Malware Using LLM
by: Wang, Haizhou, et al.
Published: (2024)

Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Cameras
by: Riaño, Roberto, et al.
Published: (2024)

Backdoor Sentinel: Detecting and Detoxifying Backdoors in Diffusion Models via Temporal Noise Consistency
by: Wang, Bingzheng, et al.
Published: (2026)

Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use
by: Zhang, Wuyang, et al.
Published: (2026)

Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
by: Li, Zi, et al.
Published: (2026)

DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data
by: Popovic, Dorde, et al.
Published: (2025)

Fast Proxies for LLM Robustness Evaluation
by: Beyer, Tim, et al.
Published: (2025)

BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting
by: Qiu, Huming, et al.
Published: (2023)

Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems
by: Jiao, Ruochen, et al.
Published: (2024)

Backdooring Bias in Large Language Models
by: Das, Anudeep, et al.
Published: (2026)

Lightweight and Fast Backdoor Model Detection
by: Yu, Yinbo, et al.
Published: (2026)

BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge
by: Tong, Terry, et al.
Published: (2025)

The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
by: Zhang, Rui, et al.
Published: (2025)

Towards Backdoor Stealthiness in Model Parameter Space
by: Xu, Xiaoyun, et al.
Published: (2025)

You Can Backdoor Personalized Federated Learning
by: Ye, Tiandi, et al.
Published: (2023)

LLM-Safety Evaluations Lack Robustness
by: Beyer, Tim, et al.
Published: (2025)

Concept-Guided Backdoor Attack on Vision Language Models
by: Shen, Haoyu, et al.
Published: (2025)

Revisiting Training-Inference Trigger Intensity in Backdoor Attacks
by: Lin, Chenhao, et al.
Published: (2025)

Clean-Label Physical Backdoor Attacks with Data Distillation
by: Dao, Thinh, et al.
Published: (2024)

Invisible Textual Backdoor Attacks based on Dual-Trigger
by: Hou, Yang, et al.
Published: (2024)

Impart: An Imperceptible and Effective Label-Specific Backdoor Attack
by: Zhao, Jingke, et al.
Published: (2024)

Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection
by: Lin, Lixing, et al.
Published: (2026)

SoK: The Last Line of Defense: On Backdoor Defense Evaluation
by: Abad, Gorka, et al.
Published: (2025)

From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
by: Shen, Guangyu, et al.
Published: (2025)

SFIBA: Spatial-based Full-target Invisible Backdoor Attacks
by: Yin, Yangxu, et al.
Published: (2025)

Stealthy Backdoor Attack to Real-world Models in Android Apps
by: Wei, Jiali, et al.
Published: (2025)

ME: Trigger Element Combination Backdoor Attack on Copyright Infringement
by: Yang, Feiyu, et al.
Published: (2025)