Copertina

From Model to Breach: Towards Actionable LLM-Generated Vulnerabilities Reporting

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Vallez, Cyril, Sternfeld, Alexander, Kucharavy, Andrei, Dolamic, Ljiljana
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs
di: Sternfeld, Alexander, et al.
Pubblicazione: (2026)

TypePilot: Leveraging the Scala Type System for Secure LLM-generated Code
di: Sternfeld, Alexander, et al.
Pubblicazione: (2025)

LLM Detectors Still Fall Short of Real World: Case of LLM-Generated Short News-Like Posts
di: Gameiro, Henrique Da Silva, et al.
Pubblicazione: (2024)

Getting Your Indices in a Row: Full-Text Search for LLM Training Data for Real World
di: Marinas, Ines Altemir, et al.
Pubblicazione: (2025)

Monitoring Transformative Technological Convergence Through LLM-Extracted Semantic Entity Triple Graphs
di: Sternfeld, Alexander, et al.
Pubblicazione: (2025)

Can the Variation of Model Weights be used as a Criterion for Self-Paced Multilingual NMT?
di: Atrio, Àlex R., et al.
Pubblicazione: (2024)

A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translation
di: Sadrizadeh, Sahar, et al.
Pubblicazione: (2023)

Low-Perplexity LLM-Generated Sequences and Where To Find Them
di: Wuhrmann, Arthur, et al.
Pubblicazione: (2025)

Exploring Data and Parameter Efficient Strategies for Arabic Dialect Identifications
di: Kanjirangat, Vani, et al.
Pubblicazione: (2025)

Assessing the Importance of Frequency versus Compositionality for Subword-based Tokenization in NMT
di: Wolleb, Benoist, et al.
Pubblicazione: (2023)

Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks
di: Kanjirangat, Vani, et al.
Pubblicazione: (2025)

Are the LLMs Capable of Maintaining at Least the Language Genus?
di: Mitrović, Sandra, et al.
Pubblicazione: (2025)

NMT-Obfuscator Attack: Ignore a sentence in translation with only one word
di: Sadrizadeh, Sahar, et al.
Pubblicazione: (2024)

Implicit Probabilistic Reasoning Does Not Reflect Explicit Answers in Large Language Models
di: Mondal, Manuel, et al.
Pubblicazione: (2024)

Going over Fine Web with a Fine-Tooth Comb: Technical Report of Indexing Fine Web for Problematic Content Search and Retrieval
di: Marinas, Inés Altemir, et al.
Pubblicazione: (2025)

Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models
di: Dai, Runpeng, et al.
Pubblicazione: (2025)

Sparse vs Contiguous Adversarial Pixel Perturbations in Multimodal Models: An Empirical Analysis
di: Botocan, Cristian-Alexandru, et al.
Pubblicazione: (2024)

From Staff Messages to Actionable Insights: A Multi-Stage LLM Classification Framework for Healthcare Analytics
di: Sakai, Hajar, et al.
Pubblicazione: (2025)

From geometry to generating functions: rectangulations and permutations
di: Asinowski, Andrei, et al.
Pubblicazione: (2024)

Contextual Breach: Assessing the Robustness of Transformer-based QA Models
di: Saadat, Asir, et al.
Pubblicazione: (2024)

Hidden Data Privacy Breaches in Federated Learning
di: Gong, Xueluan, et al.
Pubblicazione: (2024)

RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation
di: Wu, Sihong, et al.
Pubblicazione: (2026)

A Hybrid Supervised-LLM Pipeline for Actionable Suggestion Mining in Unstructured Customer Reviews
di: Trivedi, Aakash, et al.
Pubblicazione: (2026)

Leveraging Large Language Models for Actionable Course Evaluation Student Feedback to Lecturers
di: Zhang, Mike, et al.
Pubblicazione: (2024)

Towards Transparency: Exploring LLM Trainings Datasets through Visual Topic Modeling and Semantic Frame
di: de Dampierre, Charles, et al.
Pubblicazione: (2024)

Micro-Act: Mitigating Knowledge Conflict in LLM-based RAG via Actionable Self-Reasoning
di: Huo, Nan, et al.
Pubblicazione: (2025)

LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback
di: Xu, Wenda, et al.
Pubblicazione: (2023)

Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation
di: Zugecova, Aneta, et al.
Pubblicazione: (2024)

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
di: Zhang, Hengyuan, et al.
Pubblicazione: (2026)

Towards Next-Generation LLM Training: From the Data-Centric Perspective
di: Liang, Hao, et al.
Pubblicazione: (2026)

Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis
di: Scirè, Alessandro, et al.
Pubblicazione: (2024)

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content
di: Furniturewala, Shaz, et al.
Pubblicazione: (2025)

Towards Actionable Pedagogical Feedback: A Multi-Perspective Analysis of Mathematics Teaching and Tutoring Dialogue
di: Naim, Jannatun, et al.
Pubblicazione: (2025)

"Actionable Help" in Crises: A Novel Dataset and Resource-Efficient Models for Identifying Request and Offer Social Media Posts
di: Lamsal, Rabindra, et al.
Pubblicazione: (2025)

SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization
di: Liu, Houjun, et al.
Pubblicazione: (2026)

OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
di: Liu, Tianci, et al.
Pubblicazione: (2025)

RET-LLM: Towards a General Read-Write Memory for Large Language Models
di: Modarressi, Ali, et al.
Pubblicazione: (2023)

LLM-based Triplet Extraction from Financial Reports
di: Wesslund, Dante, et al.
Pubblicazione: (2026)

Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions
di: Hong, Mengze, et al.
Pubblicazione: (2025)

CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation
di: Ke, Pei, et al.
Pubblicazione: (2023)