Attack and defense techniques in large language models: A survey and new perspectives
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:QHBBFT4Yrecord.jsonopen to challenge →
read the original abstract
Large Language Models (LLMs) have become central to numerous natural language processing tasks, but their vulnerabilities present significant security and ethical challenges. This systematic survey explores the evolving landscape of attack and defense techniques in LLMs. We classify attacks into adversarial prompt attack, optimized attacks, model theft, as well as attacks on application of LLMs, detailing their mechanisms and implications. Consequently, we analyze defense strategies, including prevention-based and detection-based defense methods. Although advances have been made, challenges remain to adapt to the dynamic threat landscape, balance usability with robustness, and address resource constraints in defense implementation. We highlight open problems, including the need for adaptive scalable defenses, explainable security techniques, and standardized evaluation frameworks. This survey provides actionable insights and directions for developing secure and resilient LLMs, emphasizing the importance of interdisciplinary collaboration and ethical considerations to mitigate risks in real-world applications.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing
PRJA achieves 83.6% average success injecting harmful content into LRM reasoning chains on five QA datasets without altering final answers.
-
Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs
DACO curates a 15,000-concept dictionary from 400K image-caption pairs and uses it to initialize an SAE that enables granular, concept-specific steering of MLLM activations, raising safety scores on MM-SafetyBench and...
-
Conversations Risk Detection LLMs in Financial Agents via Multi-Stage Generative Rollout
FinSec is a multi-stage detection system for financial LLM dialogues that reaches 90.13% F1 score, cuts attack success rate to 9.09%, and raises AUPRC to 0.9189.
-
Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts
Sentra-Guard reports 99.96% detection of adversarial LLM prompts with AUC 1.00 and ASR of 0.004% using a hybrid SBERT-FAISS and transformer classifier architecture with multilingual translation and human feedback.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.