Image de couverture de livre

LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ibanez-Lissen, Luis, Gonzalez-Manzano, Lorena, de Fuentes, Jose Maria, Anciaux, Nicolas
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states
par: Ibanez-Lissen, Luis, et autres
Publié: (2024)

Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique
par: Li, Yanming, et autres
Publié: (2025)

DP-FlogTinyLLM: Differentially private federated log anomaly detection using Tiny LLMs
par: Thompson, Isaiah, et autres
Publié: (2026)

Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs
par: Ma, Tengyun, et autres
Publié: (2025)

eyeballvul: a future-proof benchmark for vulnerability detection in the wild
par: Chauvin, Timothee
Publié: (2024)

Contextualized AI for Cyber Defense: An Automated Survey using LLMs
par: Haryanto, Christoforus Yoga, et autres
Publié: (2024)

Analysis of the vulnerability of machine learning regression models to adversarial attacks using data from 5G wireless networks
par: Legashev, Leonid, et autres
Publié: (2025)

Llama-based source code vulnerability detection: Prompt engineering vs Fine tuning
par: Ouchebara, Dyna Soumhane, et autres
Publié: (2025)

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models
par: Sinha, Yash, et autres
Publié: (2025)

Kill Two Birds with One Stone! Trajectory enabled Unified Online Detection of Adversarial Examples and Backdoor Attacks
par: Fu, Anmin, et autres
Publié: (2025)

Anomaly detection in network flows using unsupervised online machine learning
par: Miguel-Diez, Alberto, et autres
Publié: (2025)

An explainable Recursive Feature Elimination to detect Advanced Persistent Threats using Random Forest classifier
par: Mutalib, Noor Hazlina Abdul, et autres
Publié: (2025)

FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement Learning
par: Khalil, Khurram, et autres
Publié: (2025)

When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs
par: Kim, Hanna, et autres
Publié: (2024)

Towards the generation of hierarchical attack models from cybersecurity vulnerabilities using language models
par: Sowka, Kacper, et autres
Publié: (2024)

STAF: Leveraging LLMs for Automated Attack Tree-Based Security Test Generation
par: Khule, Tanmay, et autres
Publié: (2025)

Network evasion detection with Bi-LSTM model
par: Chen, Kehua, et autres
Publié: (2025)

CVE-LLM : Automatic vulnerability evaluation in medical device industry using large language models
par: Ghosh, Rikhiya, et autres
Publié: (2024)

Prefix Probing: Lightweight Harmful Content Detection for Large Language Models
par: Yang, Jirui, et autres
Publié: (2025)

AEGIS: White-Box Attack Path Generation using LLMs and Training Effectiveness Evaluation for Large-Scale Cyber Defence Exercises
par: Tung, Ivan K., et autres
Publié: (2026)

Privacy-Preserving LLMs Routing
par: Wu, Xidong, et autres
Publié: (2026)

On the Privacy of LLMs: An Ablation Study
par: Makhlouf, Karima, et autres
Publié: (2026)

Nob-MIAs: Non-biased Membership Inference Attacks Assessment on Large Language Models with Ex-Post Dataset Construction
par: Eichler, Cédric, et autres
Publié: (2024)

Active Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreaks
par: Wu, ChenYu, et autres
Publié: (2025)

ActDroid: An active learning framework for Android malware detection
par: Muzaffar, Ali, et autres
Publié: (2024)

Seclens: Role-specific Evaluation of LLM's for security vulnerablity detection
par: Halder, Subho, et autres
Publié: (2026)

Persistent Pre-Training Poisoning of LLMs
par: Zhang, Yiming, et autres
Publié: (2024)

On The Dangers of Poisoned LLMs In Security Automation
par: Karlsen, Patrick, et autres
Publié: (2025)

Enhancing Adversarial Resistance in LLMs with Recursion
par: Li, Bryan, et autres
Publié: (2024)

On Automating Security Policies with Contemporary LLMs
par: Saura, Pablo Fernández, et autres
Publié: (2025)

Synthetic Cancer -- Augmenting Worms with LLMs
par: Zimmerman, Benjamin, et autres
Publié: (2024)

Privacy-Aware Randomized Quantization via Linear Programming
par: Cai, Zhongteng, et autres
Publié: (2024)

A Mixture of Linear Corrections Generates Secure Code
par: Yu, Weichen, et autres
Publié: (2025)

Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection
par: Kulkarni, Prashant
Publié: (2026)

SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models
par: Chen, Yulong, et autres
Publié: (2025)

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
par: Andriushchenko, Maksym, et autres
Publié: (2024)

The importance of the clustering model to detect new types of intrusion in data traffic
par: Abd, Noor Saud, et autres
Publié: (2024)

COPS: A Compact On-device Pipeline for real-time Smishing detection
par: S, Harichandana B S, et autres
Publié: (2024)

Multidomain transformer-based deep learning for early detection of network intrusion
par: Liu, Jinxin, et autres
Publié: (2023)

Retrieval-Augmented LLMs for Security Incident Analysis
par: Cadet, Xavier, et autres
Publié: (2026)