Imagen de Portada

Inverting Trojans in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Zhengxing, Yang, Guangmingmei, Raghuram, Jayaram, Miller, David J., Kesidis, George
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization
por: Yang, Guangmingmei, et al.
Publicado: (2025)

A Study of Backdoors in Instruction Fine-tuned Language Models
por: Raghuram, Jayaram, et al.
Publicado: (2024)

CEPA: Consensus Embedded Perturbation for Agnostic Detection and Inversion of Backdoors
por: Yang, Guangmingmei, et al.
Publicado: (2024)

Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts
por: Choi, Jihye, et al.
Publicado: (2024)

Understanding and Rectifying Safety Perception Distortion in VLMs
por: Zou, Xiaohan, et al.
Publicado: (2025)

TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning
por: Xie, Zhixin, et al.
Publicado: (2026)

Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors
por: Sahabandu, Dinuka, et al.
Publicado: (2024)

Generalisation in Multitask Fitted Q-Iteration and Offline Q-learning
por: Manda, Kausthubh, et al.
Publicado: (2025)

Forward versus Backward: Comparing Reasoning Objectives in Direct Preference Optimization
por: Nikzad, Murtaza, et al.
Publicado: (2026)

TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models
por: Dai, Yang, et al.
Publicado: (2025)

Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias
por: Chen, Yuen, et al.
Publicado: (2022)

Trojan Cleansing with Neural Collapse
por: Gu, Xihe, et al.
Publicado: (2024)

PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms
por: Li, Yilong, et al.
Publicado: (2024)

Full-Gradient Successor Feature Representations
por: Shrirao, Ritish, et al.
Publicado: (2026)

Scanning Trojaned Models Using Out-of-Distribution Samples
por: Mirzaei, Hossein, et al.
Publicado: (2025)

GPU Cluster Scheduling for Network-Sensitive Deep Learning
por: Sharma, Aakash, et al.
Publicado: (2024)

TrojanPuzzle: Covertly Poisoning Code-Suggestion Models
por: Aghakhani, Hojjat, et al.
Publicado: (2023)

TrojFSP: Trojan Insertion in Few-shot Prompt Tuning
por: Zheng, Mengxin, et al.
Publicado: (2023)

Explainability Methods for Hardware Trojan Detection: A Systematic Comparison
por: Whitten, Paul, et al.
Publicado: (2026)

How to Inverting the Leverage Score Distribution?
por: Li, Zhihang, et al.
Publicado: (2024)

Learning Distinguishable Representations in Deep Q-Networks for Linear Transfer
por: Sathish, Sooraj, et al.
Publicado: (2025)

TrojanForge: Generating Adversarial Hardware Trojan Examples Using Reinforcement Learning
por: Sarihi, Amin, et al.
Publicado: (2024)

roto 2.0: The Robot Tactile Olympiad
por: Miller, Elle, et al.
Publicado: (2026)

Trojan Horse Hunt in Time Series Forecasting for Space Operations
por: Kotowski, Krzysztof, et al.
Publicado: (2025)

On Trojan Signatures in Large Language Models of Code
por: Hussain, Aftab, et al.
Publicado: (2024)

Contextual Tokenization for Graph Inverted Indices
por: Chakraborty, Pritish, et al.
Publicado: (2025)

Trojans in Artificial Intelligence (TrojAI) Final Report
por: Reese, Kristopher W., et al.
Publicado: (2026)

Inverting the Leverage Score Gradient: An Efficient Approximate Newton Method
por: Li, Chenyang, et al.
Publicado: (2024)

Cycle-Consistent Helmholtz Machine: Goal-Seeded Simulation via Inverted Inference
por: Li, Xin
Publicado: (2025)

Inverting Non-Injective Functions with Twin Neural Network Regression
por: Wetzel, Sebastian J.
Publicado: (2026)

Adaptive Sampled Softmax with Inverted Multi-Index: Methods, Theory and Applications
por: Chen, Jin, et al.
Publicado: (2025)

From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
por: Pan, Zhuoshi, et al.
Publicado: (2023)

TROJAN-GUARD: Hardware Trojans Detection Using GNN in RTL Designs
por: Thorat, Kiran, et al.
Publicado: (2025)

Evil from Within: Machine Learning Backdoors through Hardware Trojans
por: Warnecke, Alexander, et al.
Publicado: (2023)

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks
por: Li, Ang, et al.
Publicado: (2025)

Evasive Hardware Trojan through Adversarial Power Trace
por: Omidi, Behnam, et al.
Publicado: (2024)

An AI Architecture with the Capability to Classify and Explain Hardware Trojans
por: Whitten, Paul, et al.
Publicado: (2024)

Inverting estimating equations for causal inference on quantiles
por: Cheng, Chao, et al.
Publicado: (2024)

Multi-Agent Inverted Transformer for Flight Trajectory Prediction
por: Yoon, Seokbin, et al.
Publicado: (2025)

Adaptive Inverted-Index Routing for Granular Mixtures-of-Experts
por: Kladny, Klaus-Rudolf, et al.
Publicado: (2026)