Copertina

What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chang, Jiamin, Li, Haoyang, Pearce, Hammond, Sun, Ruoxi, Li, Bo, Xue, Minhui
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SoK: The Security-Safety Continuum of Multimodal Foundation Models through Information Flow and Global Game-Theoretic Analysis of Asymmetric Threats
di: Sun, Ruoxi, et al.
Pubblicazione: (2024)

A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services
di: Hu, Hongsheng, et al.
Pubblicazione: (2023)

The Invisible Game on the Internet: A Case Study of Decoding Deceptive Patterns
di: Shi, Zewei, et al.
Pubblicazione: (2024)

Leakage-Resilient and Carbon-Neutral Aggregation Featuring the Federated AI-enabled Critical Infrastructure
di: Deng, Zehang, et al.
Pubblicazione: (2024)

50 Shades of Deceptive Patterns: A Unified Taxonomy, Multimodal Detection, and Security Implications
di: Shi, Zewei, et al.
Pubblicazione: (2025)

Iterative Window Mean Filter: Thwarting Diffusion-based Adversarial Purification
di: Wang, Hanrui, et al.
Pubblicazione: (2024)

Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning
di: Hu, Hongsheng, et al.
Pubblicazione: (2024)

Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices
di: Xia, Xiaoyu, et al.
Pubblicazione: (2024)

Fast Revocable Attribute-Based Encryption with Data Integrity for Internet of Things
di: Li, Yongjiao, et al.
Pubblicazione: (2025)

Keep the Lights On, Keep the Lengths in Check: Plug-In Adversarial Detection for Time-Series LLMs in Energy Forecasting
di: Ma, Hua, et al.
Pubblicazione: (2025)

StyleFool: Fooling Video Classification Systems via Style Transfer
di: Cao, Yuxin, et al.
Pubblicazione: (2022)

SoK: Unlearnability and Unlearning for Model Dememorization
di: Zhang, Mengying, et al.
Pubblicazione: (2026)

Provably Unlearnable Data Examples
di: Wang, Derui, et al.
Pubblicazione: (2024)

TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models
di: Li, Songze, et al.
Pubblicazione: (2024)

LASHED: LLMs And Static Hardware Analysis for Early Detection of RTL Bugs
di: Ahmad, Baleegh, et al.
Pubblicazione: (2025)

LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks
di: Ullah, Saad, et al.
Pubblicazione: (2023)

Ruledger: Ensuring Execution Integrity in Trigger-Action IoT Platforms
di: Fan, Jingwen, et al.
Pubblicazione: (2024)

Membership Inference Attacks and Defenses in Federated Learning: A Survey
di: Bai, Li, et al.
Pubblicazione: (2024)

Re-Key-Free, Risky-Free: Adaptable Model Usage Control
di: Wang, Zihan, et al.
Pubblicazione: (2025)

From Data Behavior to Code Analysis: A Multimodal Study on Security and Privacy Challenges in Blockchain-Based DApp
di: Sun, Haoyang, et al.
Pubblicazione: (2025)

Fixing Hardware Security Bugs with Large Language Models
di: Ahmad, Baleegh, et al.
Pubblicazione: (2023)

Zk-SNARK for String Match
di: Li, Taoran, et al.
Pubblicazione: (2025)

TMRugPull: A Temporally Sound Multimodal Dataset for Early RugPull Detection
di: Shoaei, Fatemeh, et al.
Pubblicazione: (2026)

METANOIA: A Lifelong Intrusion Detection and Investigation System for Mitigating Concept Drift
di: Ying, Jie, et al.
Pubblicazione: (2024)

On the Robustness of LDP Protocols for Numerical Attributes under Data Poisoning Attacks
di: Li, Xiaoguang, et al.
Pubblicazione: (2024)

Towards Better Attribute Inference Vulnerability Measures
di: Francis, Paul, et al.
Pubblicazione: (2025)

Aegis: Towards Governance, Integrity, and Security of AI Voice Agents
di: Li, Xiang, et al.
Pubblicazione: (2026)

From Storage to Steering: Memory Control Flow Attacks on LLM Agents
di: Xu, Zhenlin, et al.
Pubblicazione: (2026)

Serial Scammers and Attack of the Clones: How Scammers Coordinate Multiple Rug Pulls on Decentralized Exchanges
di: Huynh, Phuong Duy, et al.
Pubblicazione: (2024)

Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack
di: Xue, Jing, et al.
Pubblicazione: (2025)

Logic Meets Magic: LLMs Cracking Smart Contract Vulnerabilities
di: Xiao, ZeKe, et al.
Pubblicazione: (2025)

PDRIMA: A Policy-Driven Runtime Integrity Measurement and Attestation Approach for ARM TrustZone-based TEE
di: Mao, Jingkai, et al.
Pubblicazione: (2025)

LIFT: Automating Symbolic Execution Optimization with Large Language Models for AI Networks
di: Wang, Ruoxi, et al.
Pubblicazione: (2025)

The Philosopher's Stone: Trojaning Plugins of Large Language Models
di: Dong, Tian, et al.
Pubblicazione: (2023)

Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference
di: Zhang, Chenxiang, et al.
Pubblicazione: (2025)

Behavioral Integrity Verification for AI Agent Skills
di: Wu, Yuhao, et al.
Pubblicazione: (2026)

DIMSIM -- Device Integrity Monitoring through iSIM Applets and Distributed Ledger Technology
di: Faisal, Tooba, et al.
Pubblicazione: (2024)

What Gets Measured Gets Managed: Mitigating Supply Chain Attacks with a Link Integrity Management System
di: So, Johnny, et al.
Pubblicazione: (2025)

Poster: ClawdGo: Endogenous Security Awareness Training for Autonomous AI Agents
di: Li, Jiaqi, et al.
Pubblicazione: (2026)

Physically Unclonable Functions for Secure IoT Authentication and Hardware-Anchored AI Model Integrity
di: Zadeh, Maryam Taghi, et al.
Pubblicazione: (2026)