REVIEW 7 cited by
An Early Categorization of Prompt Injection Attacks on Large Language Models
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
An Early Categorization of Prompt Injection Attacks on Large Language Models
read the original abstract
Large language models and AI chatbots have been at the forefront of democratizing artificial intelligence. However, the releases of ChatGPT and other similar tools have been followed by growing concerns regarding the difficulty of controlling large language models and their outputs. Currently, we are witnessing a cat-and-mouse game where users attempt to misuse the models with a novel attack called prompt injections. In contrast, the developers attempt to discover the vulnerabilities and block the attacks simultaneously. In this paper, we provide an overview of these emergent threats and present a categorization of prompt injections, which can guide future research on prompt injections and act as a checklist of vulnerabilities in the development of LLM interfaces. Moreover, based on previous literature and our own empirical research, we discuss the implications of prompt injections to LLM end users, developers, and researchers.
Forward citations
Cited by 7 Pith papers
-
Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation Against Emerging Prompt Injection Attacks
Dynamic separator generation via domain-separated SHA-256 reduces attack success rate from 0.88 to 0.38 and eliminates leakage exposure in evaluations against 16 payloads on Llama and DeepSeek models.
-
StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation
StealthGraph generates implicit domain-relevant harmful prompts via knowledge-graph guidance and two-strategy obfuscation to enable more realistic red-teaming of LLM safety.
-
The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
AI safety should be measured by whether deployed systems keep errors visible, contestable, containable, and recoverable across five integrity layers, not only by whether individual model outputs look safe.
-
DAO-enabled decentralized physical AI: A new paradigm for human-machine collaboration
DePAI is a proposed democratic architecture that integrates DAOs, DePIN, and AI to enable human oversight of machine execution in physical-digital systems under transparent on-chain rules.
-
How Well Do AI Systems Solve AP Physics? A Comparative Evaluation of Large Language Models on Algebra-Based Free Response Questions
ChatGPT 4.1 mini, Gemini 2.5 Flash, Claude 4.0 Sonnet, and DeepSeek R1 average 82–92% on AP Physics 1/2 free-response questions but systematically fail spatial, visual, and conceptual tasks.
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
-
When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review
GPT-5-mini gives weaker papers systematically higher scores than human reviewers, and hidden field-specific prompts in PDFs can force it to assign perfect scores or suppress weaknesses.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.