:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Polyakov, Alex, Kuznetsov, Daniel
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security
Online Access:	https://arxiv.org/abs/2604.19461
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Local Frames: Exploiting Inherited Origins to Bypass Content Blockers
by: Ukani, Alisha, et al.
Published: (2025)

Exploring ChatGPT for Face Presentation Attack Detection in Zero and Few-Shot in-Context Learning
by: Komaty, Alain, et al.
Published: (2025)

WAFFLED: Exploiting Parsing Discrepancies to Bypass Web Application Firewalls
by: Akhavani, Seyed Ali, et al.
Published: (2025)

Few-Shot Learning-Based Cyber Incident Detection with Augmented Context Intelligence
by: Zuo, Fei, et al.
Published: (2025)

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift
by: Yuan, Shuai, et al.
Published: (2025)

Generalized Adversarial Code-Suggestions: Exploiting Contexts of LLM-based Code-Completion
by: Rubel, Karl, et al.
Published: (2024)

FreakOut-LLM: The Effect of Emotional Stimuli on Safety Alignment
by: Kuznetsov, Daniel, et al.
Published: (2026)

Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment
by: Zaree, Pedram, et al.
Published: (2025)

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
by: Tang, Xinyu, et al.
Published: (2023)

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG
by: Li, Junchen, et al.
Published: (2026)

Involuntary Jailbreak: On Self-Prompting Attacks
by: Guo, Yangyang, et al.
Published: (2025)

Using Hallucinations to Bypass GPT4's Filter
by: Lemkin, Benjamin
Published: (2024)

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

MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment
by: Halloran, John
Published: (2025)

Physical-Layer Signal Injection Attacks on EV Charging Ports: Bypassing Authentication via Electrical-Level Exploits
by: Shi, Hetian, et al.
Published: (2025)

In-Context Unlearning: Language Models as Few Shot Unlearners
by: Pawelczyk, Martin, et al.
Published: (2023)

Attention Masks Help Adversarial Attacks to Bypass Safety Detectors
by: Shi, Yunfan
Published: (2024)

Safety Alignment Should Be Made More Than Just a Few Tokens Deep
by: Qi, Xiangyu, et al.
Published: (2024)

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms
by: He, Sinan, et al.
Published: (2025)

Advancing Jailbreak Strategies: A Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses
by: Ahmed, Mohamed, et al.
Published: (2025)

Distributed Intrusion Detection in Dynamic Networks of UAVs using Few-Shot Federated Learning
by: Ceviz, Ozlem, et al.
Published: (2025)

Model X-Ray: Detection of Hidden Malware in AI Model Weights using Few Shot Learning
by: Gilkarov, Daniel, et al.
Published: (2024)

FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models
by: Wang, Yanting, et al.
Published: (2024)

MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
by: Radosevich, Brandon, et al.
Published: (2025)

Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing
by: Holtzman, Ari, et al.
Published: (2026)

Agent Safety Alignment via Reinforcement Learning
by: Sha, Zeyang, et al.
Published: (2025)

VIPER-MCP: Detecting and Exploiting Taint-Style Vulnerabilities in Model Context Protocol Servers
by: Sun, Pengyu, et al.
Published: (2026)

Towards Novel Malicious Packet Recognition: A Few-Shot Learning Approach
by: Stein, Kyle, et al.
Published: (2024)

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

SleepWalk: Exploiting Context Switching and Residual Power for Physical Side-Channel Attacks
by: Sanjaya, Sahan, et al.
Published: (2025)

Safety Alignment Should Be Made More Than Just A Few Attention Heads
by: Huang, Chao, et al.
Published: (2025)

Few Edges Are Enough: Few-Shot Network Attack Detection with Graph Neural Networks
by: Bilot, Tristan, et al.
Published: (2025)

Strengthening Network Intrusion Detection in IoT Environments with Self-Supervised Learning and Few Shot Learning
by: Atitallah, Safa Ben, et al.
Published: (2024)

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
by: Wang, Yanbo, et al.
Published: (2026)

MalMixer: Few-Shot Malware Classification with Retrieval-Augmented Semi-Supervised Learning
by: Li, Jiliang, et al.
Published: (2024)

TREC: APT Tactic / Technique Recognition via Few-Shot Provenance Subgraph Learning
by: Lv, Mingqi, et al.
Published: (2024)

Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders
by: Campbell, David, et al.
Published: (2026)

Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs
by: Ferrand, Jean-Charles Noirot, et al.
Published: (2025)

A Classification-by-Retrieval Framework for Few-Shot Anomaly Detection to Detect API Injection Attacks
by: Aharon, Udi, et al.
Published: (2024)

Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4
by: Mandal, Bishwas, et al.
Published: (2024)