Copertina

Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Ruixuan, Evans, David, Xiong, Li
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
di: Cai, Will, et al.
Pubblicazione: (2025)

Auditing Prompt Caching in Language Model APIs
di: Gu, Chenchen, et al.
Pubblicazione: (2025)

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
di: Xiong, Alexander, et al.
Pubblicazione: (2025)

Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent
di: Zhang, Boyang, et al.
Pubblicazione: (2026)

Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities
di: Krishna, Arjun, et al.
Pubblicazione: (2025)

MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction
di: Hu, Xiao, et al.
Pubblicazione: (2025)

The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
di: Meeus, Matthieu, et al.
Pubblicazione: (2025)

Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
di: Wu, Xiaoyu, et al.
Pubblicazione: (2025)

Log Probability Tracking of LLM APIs
di: Chauvin, Timothée, et al.
Pubblicazione: (2025)

Towards hyperparameter-free optimization with differential privacy
di: Bu, Zhiqi, et al.
Pubblicazione: (2025)

Token-Efficient Change Detection in LLM APIs
di: Chauvin, Timothée, et al.
Pubblicazione: (2026)

Differentially Private Tabular Data Synthesis using Large Language Models
di: Tran, Toan V., et al.
Pubblicazione: (2024)

Towards More Realistic Extraction Attacks: An Adversarial Perspective
di: More, Yash, et al.
Pubblicazione: (2024)

AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens
di: Li, Tung-Ling, et al.
Pubblicazione: (2025)

Improving LLM Safety Alignment with Dual-Objective Optimization
di: Zhao, Xuandong, et al.
Pubblicazione: (2025)

Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs
di: Davies, Xander, et al.
Pubblicazione: (2025)

Two Birds with One Stone: Multi-Task Detection and Attribution of LLM-Generated Text
di: Rao, Zixin, et al.
Pubblicazione: (2025)

Exploiting Novel GPT-4 APIs
di: Pelrine, Kellin, et al.
Pubblicazione: (2023)

On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models
di: Sahili, Ali Al, et al.
Pubblicazione: (2025)

GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
di: Huang, Ruixuan, et al.
Pubblicazione: (2025)

On Calibration of LLM-based Guard Models for Reliable Content Moderation
di: Liu, Hongfu, et al.
Pubblicazione: (2024)

Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
di: Wang, Tianchun, et al.
Pubblicazione: (2024)

LLMCloudHunter: Harnessing LLMs for Automated Extraction of Detection Rules from Cloud-Based CTI
di: Schwartz, Yuval, et al.
Pubblicazione: (2024)

Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA
di: Wang, Fei, et al.
Pubblicazione: (2025)

Automated CVE Analysis: Harnessing Machine Learning In Designing Question-Answering Models For Cybersecurity Information Extraction
di: Faruk, Tanjim Bin
Pubblicazione: (2024)

A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage
di: Xin, Rui, et al.
Pubblicazione: (2025)

Is poisoning a real threat to LLM alignment? Maybe more so than you think
di: Pathmanathan, Pankayaraj, et al.
Pubblicazione: (2024)

A Framework for Cost-Effective and Self-Adaptive LLM Shaking and Recovery Mechanism
di: Chen, Zhiyu, et al.
Pubblicazione: (2024)

Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation
di: Guo, Wenkai, et al.
Pubblicazione: (2025)

LLM Unlearning Should Be Form-Independent
di: Ye, Xiaotian, et al.
Pubblicazione: (2025)

GCG Attack On A Diffusion LLM
di: Neyroud, Ruben, et al.
Pubblicazione: (2025)

Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking
di: Xu, Yijie, et al.
Pubblicazione: (2025)

Sparse Autoencoders are Capable LLM Jailbreak Mitigators
di: Assogba, Yannick, et al.
Pubblicazione: (2026)

LLMGuard: Guarding Against Unsafe LLM Behavior
di: Goyal, Shubh, et al.
Pubblicazione: (2024)

Localizing Malicious Outputs from CodeLLM
di: Borana, Mayukh, et al.
Pubblicazione: (2025)

LLM Cyber Evaluations Don't Capture Real-World Risk
di: Lukošiūtė, Kamilė, et al.
Pubblicazione: (2025)

VEXA: Evidence-Grounded and Persona-Adaptive Explanations for Scam Risk Sensemaking
di: An, Heajun, et al.
Pubblicazione: (2026)

PVMark: Enabling Public Verifiability for LLM Watermarking Schemes
di: Duan, Haohua, et al.
Pubblicazione: (2025)

Evaluation of LLM Chatbots for OSINT-based Cyber Threat Awareness
di: Shafee, Samaneh, et al.
Pubblicazione: (2024)

Watermark under Fire: A Robustness Evaluation of LLM Watermarking
di: Liang, Jiacheng, et al.
Pubblicazione: (2024)