REVIEW 13 cited by
Security and Privacy Challenges of Large Language Models: A Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Large Language Models (LLMs) have demonstrated extraordinary capabilities and contributed to multiple fields, such as generating and summarizing text, language translation, and question-answering. Nowadays, LLM is becoming a very popular tool in computerized language processing tasks, with the capability to analyze complicated linguistic patterns and provide relevant and appropriate responses depending on the context. While offering significant advantages, these models are also vulnerable to security and privacy attacks, such as jailbreaking attacks, data poisoning attacks, and Personally Identifiable Information (PII) leakage attacks. This survey provides a thorough review of the security and privacy challenges of LLMs for both training data and users, along with the application-based risks in various domains, such as transportation, education, and healthcare. We assess the extent of LLM vulnerabilities, investigate emerging security and privacy attacks for LLMs, and review the potential defense mechanisms. Additionally, the survey outlines existing research gaps in this domain and highlights future research directions.
Forward citations
Cited by 13 Pith papers
-
Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning
A Jacobian-lens audit predicts model-level relearning recovery in LLM unlearning but cannot pick which facts return and backfires when used as a training penalty.
-
To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
Polymorphic Prompt Assembling randomizes per-request system-prompt separators, cutting prompt-injection attack success to as low as 1.83% on GPT-3.5 with 0.06 ms runtime overhead.
-
Measuring Human Involvement in AI-Generated Text: A Case Study on Academic Writing
Human involvement in AI-generated academic text can be estimated continuously by training a RoBERTa regressor on BERTScore-derived labels, outperforming binary detectors on a new synthetic dataset.
-
LLM Access Shield: Domain-Specific LLM Framework for Privacy Policy Compliance
An enterprise proxy that detects sensitive data in LLM prompts with a fine-tuned small model and replaces it with format-preserving encryption.
-
Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks
Simple prompt-injection attacks against real-world LLM agents like Anthropic Computer Use, MultiOn, and ChemCrow succeed at leaking data and enabling harmful actions.
-
Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models
PEFT methods (LoRA, Adapter) achieve lower membership-inference AUC than full fine-tuning, indicating reduced memorisation, but DP's protective effect is weaker for PEFT models.
-
GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs
A three-bit targeted memory corruption, located by a genetic search, collapses an 8B-parameter quantized LLM's benchmark performance to zero.
-
Large Language Model Adversarial Landscape Through the Lens of Attack Objectives
A survey that re-frames LLM adversarial attacks and defenses around four attacker objectives: privacy, integrity, availability, and misuse.
-
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
A survey that organizes responsible-LLM research into five risk dimensions and four intervention phases, reviewing privacy, hallucination, value, toxicity, and jailbreak mitigation.
-
SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation
A systematization-of-knowledge survey that categorizes LLM privacy risks into training data, prompts, outputs, and agents, and reviews limitations of current mitigations.
-
LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures
This survey categorizes attacks on large language models by lifecycle phase and maps them to prevention and detection defenses, concluding that only a few defenses are highly effective.
-
Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions
The paper surveys recent work, models, applications, and challenges of using LLMs in intelligent transportation systems, without presenting new experimental results.
-
Survey of different Large Language Model Architectures: Trends, Benchmarks, and Challenges
A broad but error-prone survey of LLM and MLLM architectures, training methods, benchmarks, and challenges.
Discussion (0). Continue with ORCID to comment.