Cover Image

Permissive Information-Flow Analysis for Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Siddiqui, Shoaib Ahmed, Gaonkar, Radhika, Köpf, Boris, Krueger, David, Paverd, Andrew, Salem, Ahmed, Tople, Shruti, Wutschitz, Lukas, Xia, Menglin, Zanella-Béguelin, Santiago
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Securing AI Agents with Information-Flow Control
by: Costa, Manuel, et al.
Published: (2025)

Closed-Form Bounds for DP-SGD against Record-level Inference
by: Cherubin, Giovanni, et al.
Published: (2024)

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

Optimizing Agent Planning for Security and Autonomy
by: Kolluri, Aashish, et al.
Published: (2026)

Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs
by: Salem, Ahmed, et al.
Published: (2026)

On Evaluating LLMs' Capabilities as Functional Approximators: A Bayesian Perspective
by: Siddiqui, Shoaib Ahmed, et al.
Published: (2024)

Position: Capability Control Should be a Separate Goal From Alignment
by: Siddiqui, Shoaib Ahmed, et al.
Published: (2026)

Protecting against simultaneous data poisoning attacks
by: Alex, Neel, et al.
Published: (2024)

MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
by: Wen, Rui, et al.
Published: (2026)

Blockwise Self-Supervised Learning at Scale
by: Siddiqui, Shoaib Ahmed, et al.
Published: (2023)

Get my drift? Catching LLM Task Drift with Activation Deltas
by: Abdelnabi, Sahar, et al.
Published: (2024)

Exploring the design space of deep-learning-based weather forecasting systems
by: Siddiqui, Shoaib Ahmed, et al.
Published: (2024)

Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
by: Pradhan, Gauri, et al.
Published: (2025)

Invariant Aggregator for Defending against Federated Backdoor Attacks
by: Wang, Xiaoyang, et al.
Published: (2022)

Enhanced Accuracy and Real‐Time Monitoring: A Hybrid Communication Architecture for Fertility Monitoring
by: Shama Siddiqui, et al.
Published: (2024)

Towards Investigating Innovation Perceptions of Leaders in the ICT Sector of Pakistan
by: Eram Abbasi, et al.
Published: (2025)

Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models
by: Russinovich, Mark, et al.
Published: (2025)

The Topological Trouble With Transformers
by: Mozer, Michael C., et al.
Published: (2026)

Highlight & Summarize: RAG without the jailbreaks
by: Cherubin, Giovanni, et al.
Published: (2025)

How Violence Shapes Place: The Rise of Neo‐Authoritarianism in the Global Value Chain and the Emergence of an ‘Infernal Place’ in the Bangladesh Garment Industry
by: Shoaib Ahmed
Published: (2025)

A deeper look at depth pruning of LLMs
by: Siddiqui, Shoaib Ahmed, et al.
Published: (2024)

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
by: Siddiqui, Shoaib Ahmed, et al.
Published: (2025)

A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks
by: Bullwinkel, Blake, et al.
Published: (2025)

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting
by: Cretu, Ana-Maria, et al.
Published: (2023)

Chapter 5 Islam, Poverty, and Philanthropy in the Global South
by: Siddiqui, Shariq Ahmed
Published: (2024)

MECHANICAL PERFORMANCE AND PRINTABILITY FACTORS IN 3D PRINTED CONCRETE: A SYSTEMATIC REVIEW OF MIX DESIGN, PROCESS PARAMETERS, AND CURING CONDITIONS
by: Shabbir Ahmed Siddiqui
Published: (2026)

Transnational Flows and Permissive Polities
Published: (2014)

Transnational Flows and Permissive Polities
by: Kalir, Barak, et al.
Published: (2025)

SOS! Soft Prompt Attack Against Open-Source Large Language Models
by: Yang, Ziqing, et al.
Published: (2024)

TAMAÑO CORPORAL Y TEMPERATURA AMBIENTAL EN POBLACIONES CAZADORAS RECOLECTORAS DEL HOLOCENO TARDIO DE PAMPA Y PATAGONIA
by: Marien Béguelin
Published: (2010)

ESTIMACION DEL SEXO EN POBLACIONES DEL SUR DE SUDAMERCIA MEDIANTE FUNCIONES DISCRIMINANTES PARA EL FEMUR
by: Marien Béguelin
Published: (2008)

PONIENDO BLANCO SOBRE NEGRO: ANÁLISIS QUÍMICOS Y MICROSCÓPICOS SOBRE SEDIMENTOS Y RESTOS HUMANOS DE LA LAGUNA DEL JUNCAL (VALLE DEL RÍO NEGRO, NORPATAGONIA)
by: Marien Béguelin
Published: (2022)

ESTIMACION DE LA ESTATURA EN MUESTRAS DEL HOLOCENO TARDIO DEL N.O. DE SANTA CRUZ: PROBLEMAS METODOLOGICOS
by: Marien Béguelin
Published: (2005)

Estimación del sexo en cazadores-recolectores de Sudamérica a partir de variables métricas del húmero
by: Marien Béguelin
Published: (2011)

Variación morfométrica postcraneal en muestras tardías de restos humanos de Patagonia: una aproximación biogeográfica
by: Marien Béguelin
Published: (2006)

Understanding Concept Drift with Deprecated Permissions in Android Malware Detection
by: Sabbah, Ahmed, et al.
Published: (2025)

Obligations and Permissions, and Conflicting Norms
by: Andrew Halpin
Published: (2025)

Permissive-Washing in the Open AI Supply Chain: A Large-Scale Audit of License Integrity
by: Jewitt, James, et al.
Published: (2026)

Byzantine-Fault-Tolerant Consensus via Reinforcement Learning for Permissioned Blockchain Implemented in a V2X Network
by: Kim, Seungmo, et al.
Published: (2020)

The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness
by: Abdelnabi, Sahar, et al.
Published: (2025)