paper-with-me

홈 › Papers

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs

2025-09-04 · Brennen Hill, Surendra Parla, Venkata Abhijeeth Balabhadruni, Atharv Prajod Padmalayam, Sujay Chandra Shekara Sharma arxiv

The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks exploit vulnerabilities in a model's design, training, and contextual understanding, leading to intellectual property theft, misinformation generation, and erosion of user trust. A systematic understanding of these attack vectors is the foundational step toward developing robust countermeasures. This paper presents a comprehensive literature survey of prompt-based attack methodologies, categorizing them to provide a clear threat model. By detailing the mechanisms and impacts of these exploits, this survey aims to inform the research community's efforts in building the next generation of secure LLMs that are inherently resistant to unauthorized distillation, fine-tuning, and editing.

📄 PDF Abstract BibTeX arXiv:2509.04615

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Design Patterns for Securing LLM Agents against Prompt Injections

2025-06-10 · Luca Beurer-Kellner, Beat Buesser Ana-Maria Creţu, Edoardo Debenedetti, Daniel Dobos 외

As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing thr…

Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security

2026-05-27 · Xiang Fang, Wanlong Fang arxiv

Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbr…

Computational EfficiencyIntent ClassificationIntent Detection

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval

2025-05-21 · Taiye Chen, Zeming Wei, Ang Li, Yisen Wang

Large Language Models (LLMs) are known to be vulnerable to jailbreaking attacks, wherein adversaries exploit carefully engineered prompts to induce harmful or unethical responses. Such threats have raised critical concer…

RAGRetrievalRetrieval-augmented Generation

Exploring Vulnerabilities and Protections in Large Language Models: A Survey

2024-06-01 · Frank Weizhen Liu, Chenhui Hu

As Large Language Models (LLMs) increasingly become key components in various AI applications, understanding their security vulnerabilities and the effectiveness of defense mechanisms is crucial. This survey examines the…

Data PoisoningSurvey

Encrypted Prompt: Securing LLM Applications Against Unauthorized Actions

2025-03-29 · Shih-Han Chan

Security threats like prompt injection attacks pose significant risks to applications that integrate Large Language Models (LLMs), potentially leading to unauthorized actions such as API misuse. Unlike previous approache…