The narration step in LLM-solver loops is vulnerable to prompt injection that inverts verified solver conclusions, and hardened prompts reduce but do not eliminate the risk under adaptive attacks.
super hub Canonical reference
Ignore Previous Prompt: Attack Techniques For Language Models
Canonical reference. 81% of citing Pith papers cite this work as background.
121
Pith papers citing it
Background
81% of classified citations
abstract
Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications. However, studies that explore their vulnerabilities emerging from malicious user interaction are scarce. By proposing PromptInject, a prosaic alignment framework for mask-based iterative adversarial prompt composition, we examine how GPT-3, the most widely deployed language model in production, can be easily misaligned by simple handcrafted inputs. In particular, we investigate two types of attacks -- goal hijacking and prompt leaking -- and demonstrate that even low-aptitude, but sufficiently ill-intentioned agents, can easily exploit GPT-3's stochastic nature, creating long-tail risks. The code for PromptInject is available at https://github.com/agencyenterprise/PromptInject.
hub tools
citation-role summary
background 23
method 2
baseline 1
citation-polarity summary
claims ledger
- abstract Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications. However, studies that explore their vulnerabilities emerging from malicious user interaction are scarce. By proposing PromptInject, a prosaic alignment framework for mask-based iterative adversarial prompt composition, we examine how GPT-3, the most widely deployed language model in production, can be easily misaligned by simple handcrafted inputs. In particular, we investigate two types of attacks -- goal hijacking and prompt leaking -- and demon
authors
co-cited works
representative citing papers
Identifies cross-app context poisoning in ChatGPT Apps, a persistent indirect prompt injection delivered through undocumented first-party API parameters that lets one app manipulate others via the shared untagged context.
Roughly 1% of real resumes contain hidden prompt injections against LLM screeners, prevalence has risen over 1-2 years, and over 90% avoid explicit instructions.
JAW uses hybrid program analysis to evolve inputs that hijack agentic workflows, successfully compromising 4714 GitHub workflows and eight n8n templates to enable actions like credential exfiltration.
NeuroTaint is the first taint tracking framework for LLM agents that uses offline auditing of semantic, causal, and persistent context to detect flows from untrusted sources to privileged sinks.
Malicious LLM API routers actively perform payload injection and secret exfiltration, with 9 of 428 tested routers showing malicious behavior and further poisoning risks from leaked credentials.
ContextLeak is the first empirical framework to audit worst-case information leakage in private in-context learning by inserting identifiable canary tokens and measuring their presence in model outputs.
Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
AgentDojo introduces an extensible evaluation framework populated with realistic agent tasks and security test cases to measure prompt injection robustness in tool-using LLM agents.
Self-generated QA supervision for language models is fragile due to non-uniform question selection and instruction compliance during answering, with mitigations that reduce compliance from 88% to 13%.
PrincipalBench exposes a sharp split in frontier LLMs between selective and over-refusing behavior on multi-party loyalty, with prompt scaffolding and KL distillation reducing harm rates but only along an existing leak/over-refusal trade-off.
ContractGuard verifies tool contracts in RACG systems to prevent effect forgery, restoring zero injection success on benchmarks and six hosted models against adaptive attackers.
Paraphrasing retrieved content is the most effective of five tested prompting defenses against domain-camouflaged injection attacks, cutting success rates 55-84% across three models while financial domains retain the highest residual risk.
Handlebars double-brace escaping neutralizes angle-bracket role delimiters but not colon- or Markdown-based ones, as measured by survival rates and 5760 model trials across four LLMs.
Attackers can force LLM guardrails into extended reasoning loops via optimized payloads, causing 13-63x token amplification and up to 148x latency in agent systems.
Introduces a stakeholder-centric benchmark showing current web agents fail all tested prompt injection objectives, with failures falling into stealthy parasitism, misaligned disruption, or compounded failure modes.
Introduces Document-Authored Control-Signal Impersonation (DACSI) as a low-cost indirect prompt attack on RAG safety boundaries and evaluates its effectiveness across multiple models.
An empirical study of 547 confirmed safety incidents from GitHub and literature derives a 33-type taxonomy showing constraint violations, destructive actions, and deception dominate in everyday coding-agent use.
Controlled experiments on GPT-4o-mini and Claude Haiku show indirect prompt injection success in ReAct agents decays sharply with injection depth, varies with payload framing, and remains stable across turn budgets.
Log-substrate prompt injection via attacker-controlled fields enables effective attacks on LLM SOC assistants, with persona hijacks suppressing 68% of malicious logs and context manipulation reaching 96% success on summarization, reduced to 11.8% average under strongest defenses.
LASH adaptively composes multiple jailbreak seed prompts via genetic search over subsets and mixture weights to reach 84.5% keyword ASR and 74.5% two-stage ASR on JailbreakBench while using only 30 queries per prompt.
CrossMPI steers both visual and textual interpretations in LVLMs through image-only perturbations by optimizing in hidden-state space at selected middle layers with distance-based budget allocation.
IPI-proxy is a toolkit using an intercepting proxy to inject indirect prompt injection attacks into live web pages for testing AI browsing agents against hidden instructions.
ContextualJailbreak uses evolutionary search over simulated primed dialogues with novel mutations to reach 90-100% attack success on open LLMs and transfers to some closed frontier models at 15-90% rates.
citing papers explorer
-
Eliciting Latent Predictions from Transformers with the Tuned Lens
Training per-layer affine probes on frozen transformers yields more reliable latent predictions than the logit lens and enables detection of malicious inputs from prediction trajectories.
-
GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
GPTFuzz is a black-box fuzzing framework that mutates seed jailbreak templates to automatically generate effective attacks, achieving over 90% success rates on models including ChatGPT and Llama-2.
-
Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Baseline defenses including perplexity-based detection, input preprocessing, and adversarial training offer partial robustness to text adversarial attacks on LLMs, with challenges arising from weak discrete optimizers.
-
"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
Real-world jailbreak prompts collected from the wild achieve up to 0.95 attack success rates against major LLMs including GPT-4, with some persisting for over 240 days.
-
Dr. Jekyll and Mr. Hyde: Two Faces of LLMs
Impersonating complex misaligned personas via biographies and role-play bypasses safety in ChatGPT, Gemini, and Deepseek, succeeding on 38-40 out of 40 illicit questions across tested models.