Cover Image

Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Paim, Kayua Oleques, Mansilha, Rodrigo Brandao, Kreutz, Diego, Franco, Muriel Figueredo, Cordeiro, Weverton
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Machine Learning 68T01 I.2
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Synthetic Data: AI's New Weapon Against Android Malware
by: Nogueira, Angelo Gaspar Diniz, et al.
Published: (2025)

MalDataGen: A Modular Framework for Synthetic Tabular Data Generation in Malware Detection
by: Paim, Kayua Oleques, et al.
Published: (2025)

Acoustic Identification of Ae. aegypti Mosquitoes using Smartphone Apps and Residual Convolutional Neural Networks
by: Paim, Kayuã Oleques, et al.
Published: (2023)

Reducing Instability in Synthetic Data Evaluation with a Super-Metric in MalDataGen
by: da Silva, Anna Luiza Gomes, et al.
Published: (2025)

Structured Extraction of Vulnerabilities in OpenVAS and Tenable WAS Reports Using LLMs
by: Machado, Beatriz, et al.
Published: (2025)

AnonLFI 2.0: Extensible Architecture for PII Pseudonymization in CSIRTs with OCR and Technical Recognizers
by: Kapelinski, Cristhian, et al.
Published: (2025)

Toward a Dynamic Stackelberg Game-Theoretic Framework for Agentic AI Defense Against LLM Jailbreaking
by: Han, Zhengye, et al.
Published: (2025)

The Selective G-Bispectrum and its Inversion: Applications to G-Invariant Networks
by: Mataigne, Simon, et al.
Published: (2024)

A Space-Efficient Algorithm for Longest Common Almost Increasing Subsequence of Two Sequences
by: Rahat, Md Tanzeem, et al.
Published: (2025)

MH-FSF: A Unified Framework for Overcoming Benchmarking and Reproducibility Limitations in Feature Selection Evaluation
by: Rocha, Vanderson, et al.
Published: (2025)

On-Premise SLMs vs. Commercial LLMs: Prompt Engineering and Incident Classification in SOCs and CSIRTs
by: Almeida, Gefté, et al.
Published: (2025)

ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators
by: Scassola, Davide, et al.
Published: (2026)

Shortest Paths in a Weighted Simplicial Complex
by: Chakraborty, Sukrit, et al.
Published: (2025)

MH-1M: A 1.34 Million-Sample Comprehensive Multi-Feature Android Malware Dataset for Machine Learning, Deep Learning, Large Language Models, and Threat Intelligence Research
by: Braganca, Hendrio, et al.
Published: (2025)

AI-based modular warning machine for risk identification in proximity healthcare
by: Razzetta, Chiara, et al.
Published: (2025)

Modeling Membrane Degradation in PEM Electrolyzers with Physics-Informed Neural Networks
by: Polo-Molina, Alejandro, et al.
Published: (2025)

Strategic inputs: feature selection from game-theoretic perspective
by: Zhao, Chi, et al.
Published: (2025)

Comparative Analysis of Audio Feature Extraction for Real-Time Talking Portrait Synthesis
by: Salehi, Pegah, et al.
Published: (2024)

Semantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring
by: Aksoy, Sinan G., et al.
Published: (2026)

RHealthTwin: Towards Responsible and Multimodal Digital Twins for Personalized Well-being
by: Ferdousi, Rahatara, et al.
Published: (2025)

Evaluating AI Grading on Real-World Handwritten College Mathematics: A Large-Scale Study Toward a Benchmark
by: Yu, Zhiqi, et al.
Published: (2026)

Script-Based Dialog Policy Planning for LLM-Powered Conversational Agents: A Basic Architecture for an "AI Therapist"
by: Wasenmüller, Robert, et al.
Published: (2024)

Temperature in SLMs: Impact on Incident Categorization in On-Premises Environments
by: Pohlmann, Marcio, et al.
Published: (2025)

Transit Functions and Clustering Systems
by: Changat, Manoj, et al.
Published: (2024)

Optimization before Evaluation: Evaluation with Unoptimised Prompts Can be Misleading
by: Sadjoli, Nicholas, et al.
Published: (2026)

Differential Parity: Relative Fairness Between Two Sets of Decisions
by: Yu, Zhe, et al.
Published: (2021)

Freeze, Diffuse, Decode: Geometry-Aware Adaptation of Pretrained Transformer Embeddings for Antimicrobial Peptide Design
by: Gawade, Pankhil, et al.
Published: (2025)

Creativity in the Age of AI: Rethinking the Role of Intentional Agency
by: Pearson, James S., et al.
Published: (2026)

Mathematical reasoning and the computer
by: Buzzard, Kevin
Published: (2025)

Intrinsic Rewards for Exploration without Harm from Observational Noise: A Simulation Study Based on the Free Energy Principle
by: Tinker, Theodore Jerome, et al.
Published: (2024)

Modeling Clinical Concern Trajectories in Language Model Agents
by: Subaharan, Sukesh, et al.
Published: (2026)

How well can a large language model explain business processes as perceived by users?
by: Fahland, Dirk, et al.
Published: (2024)

humancompatible.detect: a Python Toolkit for Detecting Bias in AI Models
by: Matilla, German M., et al.
Published: (2025)

Physics-Informed Neural Networks and Neural Operators for Parametric PDEs
by: Zhang, Zhuo, et al.
Published: (2025)

Application of machine learning for infrastructure reconstruction programs management
by: Khudiakov, Illia, et al.
Published: (2025)

On the Optimal Memorization Capacity of Transformers
by: Kajitsuka, Tokio, et al.
Published: (2024)

BernGraph: Probabilistic Graph Neural Networks for EHR-based Medication Recommendations
by: Piao, Xihao, et al.
Published: (2024)

Semantic Mobile Base Station Placement
by: Soman, Kritik, et al.
Published: (2021)

Representation Integrity in Temporal Graph Learning Methods
by: Kooshafar, Elahe
Published: (2025)

A Data-Driven Measure of Relative Uncertainty for Misclassification Detection
by: Dadalto, Eduardo, et al.
Published: (2023)