Copertina

The Structural Safety Generalization Problem

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Broomfield, Julius, Gibbs, Tom, Kosak-Hine, Ethan, Ingebretsen, George, Nasir, Tia, Zhang, Jason, Iranmanesh, Reihaneh, Pieri, Sara, Rabbany, Reihaneh, Pelrine, Kellin
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks
di: Gibbs, Tom, et al.
Pubblicazione: (2024)

Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility
di: Murphy, Brendan, et al.
Pubblicazione: (2025)

Online Influence Campaigns: Strategies and Vulnerabilities
di: Musulan, Andreea, et al.
Pubblicazione: (2024)

Hybrid Encryption with Certified Deletion in Preprocessing Model
di: Dey, Kunal, et al.
Pubblicazione: (2026)

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
di: Struppek, Lukas, et al.
Pubblicazione: (2026)

Robust and Reusable Fuzzy Extractors for Low-entropy Rate Randomness Sources
di: Panja, Somnath, et al.
Pubblicazione: (2024)

Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation
di: Rivera, Mauricio, et al.
Pubblicazione: (2024)

Comparing GPT-4 and Open-Source Language Models in Misinformation Mitigation
di: Vergho, Tyler, et al.
Pubblicazione: (2024)

Secure Composition of Quantum Key Distribution and Symmetric Key Encryption
di: Dey, Kunal, et al.
Pubblicazione: (2025)

CCA-Secure Hybrid Encryption in Correlated Randomness Model and KEM Combiners
di: Panja, Somnath, et al.
Pubblicazione: (2024)

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
di: Hossain, Saad, et al.
Pubblicazione: (2026)

Scaling Trends for Data Poisoning in LLMs
di: Bowen, Dillon, et al.
Pubblicazione: (2024)

Not What You Asked For: Typographic Attacks in Household Robot Manipulation
di: Iranmanesh, Ali, et al.
Pubblicazione: (2026)

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

MAGIQ: A Post-Quantum Multi-Agentic AI Governance System with Provable Security
di: Avizheh, Sepideh, et al.
Pubblicazione: (2026)

Uncertainty Resolution in Misinformation Detection
di: Orlovskiy, Yury, et al.
Pubblicazione: (2024)

Accountable authentication with privacy protection: The Larch system for universal login
di: Dauterman, Emma, et al.
Pubblicazione: (2023)

Generalized Implicit Factorization Problem
di: Feng, Yansong, et al.
Pubblicazione: (2023)

Exploiting CPU Clock Modulation for Covert Communication Channel
di: Alam, Shariful, et al.
Pubblicazione: (2024)

PoseGuard: Pose-Guided Generation with Safety Guardrails
di: Wang, Kongxin, et al.
Pubblicazione: (2025)

Matching Ranks Over Probability Yields Truly Deep Safety Alignment
di: Vega, Jason, et al.
Pubblicazione: (2025)

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI
di: Zhang, Zelin, et al.
Pubblicazione: (2026)

Maybenot: A Framework for Traffic Analysis Defenses
di: Pulls, Tobias, et al.
Pubblicazione: (2023)

Enabling High-Frequency Trading with Near-Instant, Trustless Cross-Chain Transactions via Pre-Signing Adaptor Signatures
di: Francolla, Ethan, et al.
Pubblicazione: (2025)

AutoPentest: Enhancing Vulnerability Management With Autonomous LLM Agents
di: Henke, Julius
Pubblicazione: (2025)

System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective
di: Wu, Fangzhou, et al.
Pubblicazione: (2024)

FP-Agent: Fingerprinting AI Browsing Agents
di: Wang, Ethan, et al.
Pubblicazione: (2026)

Process-Mining of Hypertraces: Enabling Scalable Formal Security Verification of (Automotive) Network Architectures
di: Figge, Julius, et al.
Pubblicazione: (2026)

zkStruDul: Programming zkSNARKs with Structural Duality
di: Krishnan, Rahul, et al.
Pubblicazione: (2025)

A Simulation System Towards Solving Societal-Scale Manipulation
di: Touzel, Maximilian Puelma, et al.
Pubblicazione: (2024)

Ethical Hacking and its role in Cybersecurity
di: Asif, Fatima, et al.
Pubblicazione: (2024)

Weak Supervision for Real World Graphs
di: Nair, Pratheeksha, et al.
Pubblicazione: (2025)

Nonmalleable Progress Leakage
di: Cecchetti, Ethan
Pubblicazione: (2025)

Behavioral Authentication for Security and Safety
di: Wang, Cheng, et al.
Pubblicazione: (2023)

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis
di: Xu, Zhenhao, et al.
Pubblicazione: (2026)

Generating Text from Uniform Meaning Representation
di: Markle, Emma, et al.
Pubblicazione: (2025)

The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents
di: Wu, Baoyuan, et al.
Pubblicazione: (2026)

The Kubernetes Security Landscape: AI-Driven Insights from Developer Discussions
di: Curtis, J. Alexander, et al.
Pubblicazione: (2024)

Generate "Normal", Edit Poisoned: Branding Injection via Hint Embedding in Image Editing
di: Sun, Desen, et al.
Pubblicazione: (2026)

Rethinking Fraud Safety Evaluation: Multi-Round Attacks Reveal Safety-Utility Tradeoffs in Graph-Context LLM Defenders
di: Jiang, Laura, et al.
Pubblicazione: (2026)