--- title: "llm-attacks vs DeepInception" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/llm-attacks-llm-attacks-vs-tmlr-group-deepinception" tools: ["llm-attacks-llm-attacks", "tmlr-group-deepinception"] --- # llm-attacks vs DeepInception *GraphCanon updated Aug 5, 2026* ## Verdict Pick llm-attacks if llm-attacks: Universal and Transferable Attacks on Aligned Language Models with dependency on FastChat; pick DeepInception if deepInception is an exploration framework for modifying large language model responses to understand their behavior and influence their outputs. [llm-attacks](https://llm-attacks.org/) reports 4.8k GitHub stars, 633 forks, and 69 open issues, last pushed Aug 2, 2024. [DeepInception](https://arxiv.org/pdf/2311.03191.pdf) has 177 stars, 19 forks, and 0 open issues, last pushed Feb 20, 2024. Figures are from public GitHub metadata via [llm-attacks's repository](https://github.com/llm-attacks/llm-attacks) and [DeepInception's repository](https://github.com/tmlr-group/DeepInception). | | [llm-attacks](/tools/llm-attacks-llm-attacks.md) | [DeepInception](/tools/tmlr-group-deepinception.md) | | --- | --- | --- | | Tagline | Universal and Transferable Attacks on Aligned Language Models | Develops techniques to influence large language model behavior | | Stars | 4,756 | 177 | | Forks | 633 | 19 | | Open issues | 69 | 0 | | Language | Python | Python | | Adopt for | llm-attacks: Universal and Transferable Attacks on Aligned Language Models with dependency on FastChat. | DeepInception is an exploration framework for modifying large language model responses to understand their behavior and influence their outputs. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | Evaluation & Observability, LLM Frameworks | LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [llm-attacks](/tools/llm-attacks-llm-attacks.md) | [DeepInception](/tools/tmlr-group-deepinception.md) | | --- | --- | --- | | Days since push | 732d | 896d | | Open issues (now) | 69 | 0 | | Full report | [trust report](/tools/llm-attacks-llm-attacks/trust.md) | [trust report](/tools/tmlr-group-deepinception/trust.md) | ## Shared compatibility - **Python**: [llm-attacks](/tools/llm-attacks-llm-attacks.md) - Python runtime; [DeepInception](/tools/tmlr-group-deepinception.md) - Python runtime ## Decision facts: llm-attacks - **Adopt for:** llm-attacks: Universal and Transferable Attacks on Aligned Language Models with dependency on FastChat. ## Decision facts: DeepInception - **Pricing:** freemium - The tool is free under the MIT license. However, using it may incur costs from third-party services like OpenAI API keys for accessing closed-source models - **Requirements:** Requires PyTorch ≥1.10 with GPU support; Environment modification needed to include path configurations for Vicuna, Llama-2, and Falcon - **Adopt for:** DeepInception is an exploration framework for modifying large language model responses to understand their behavior and influence their outputs. ## Choose when ### Choose llm-attacks if… - Tags unique to llm-attacks: alignment-testing, attacks, fastchat-dependency, language-models. - Also covers Evaluation & Observability. - When you need to test the robustness of aligned language models specifically using attacks designed for these systems, ### Choose DeepInception if… - Pricing: The tool is free under the MIT license. However, using it may incur costs from third-party services like OpenAI API keys for accessing closed-source models. - Requirements: Requires PyTorch ≥1.10 with GPU support; Environment modification needed to include path configurations for Vicuna, Llama-2, and Falcon. - Tags unique to DeepInception: deep, gpt, inception, jailbreak. - When you need to research the effects of specific modifications on the safety and trustworthiness of GPT-3, GPT-4, Vicuna, Llama-2, or Falcon models ## When NOT to use llm-attacks - Do not use if you are evaluating generic or unaligned language models without a need for alignment-specific attack testing, - Avoid when FastChat is not used in your project as llm-attacks explicitly depends on it. ## When NOT to use DeepInception - For deployment in production environments where strict adherence to ethical and regulatory guidelines is mandatory, due to the experimental nature of DeepInception - When there's a need for direct application without exploring modification effects, as DeepInception requires setting up an environment that supports specific models and modifications ## Common questions ### What is the difference between llm-attacks and DeepInception? llm-attacks: Universal and Transferable Attacks on Aligned Language Models. DeepInception: Develops techniques to influence large language model behavior. See the comparison table for live GitHub stats and shared categories. ### When should I choose llm-attacks over DeepInception? Choose llm-attacks over DeepInception when Tags unique to llm-attacks: alignment-testing, attacks, fastchat-dependency, language-models; Also covers Evaluation & Observability; When you need to test the robustness of aligned language models specifically using attacks designed for these systems,. ### When should I choose DeepInception over llm-attacks? Choose DeepInception over llm-attacks when Pricing: The tool is free under the MIT license. However, using it may incur costs from third-party services like OpenAI API keys for accessing closed-source models; Requirements: Requires PyTorch ≥1.10 with GPU support; Environment modification needed to include path configurations for Vicuna, Llama-2, and Falcon; Tags unique to DeepInception: deep, gpt, inception, jailbreak; When you need to research the effects of specific modifications on the safety and trustworthiness of GPT-3, GPT-4, Vicuna, Llama-2, or Falcon models. ### When should I avoid llm-attacks? Do not use if you are evaluating generic or unaligned language models without a need for alignment-specific attack testing, Avoid when FastChat is not used in your project as llm-attacks explicitly depends on it. ### When should I avoid DeepInception? For deployment in production environments where strict adherence to ethical and regulatory guidelines is mandatory, due to the experimental nature of DeepInception When there's a need for direct application without exploring modification effects, as DeepInception requires setting up an environment that supports specific models and modifications ### Is llm-attacks or DeepInception more popular on GitHub? llm-attacks has more GitHub stars (4,756 vs 177). Stars measure visibility, not whether either tool fits your constraints. ### Are llm-attacks and DeepInception open source? Yes - both are open-source projects on GitHub (llm-attacks: MIT, DeepInception: MIT). ### Where can I find alternatives to llm-attacks or DeepInception? GraphCanon lists graph-backed alternatives at [llm-attacks alternatives](/tools/llm-attacks-llm-attacks/alternatives) and [DeepInception alternatives](/tools/tmlr-group-deepinception/alternatives) ([llm-attacks markdown twin](/tools/llm-attacks-llm-attacks/alternatives.md), [DeepInception markdown twin](/tools/tmlr-group-deepinception/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/llm-attacks-llm-attacks-vs-tmlr-group-deepinception.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, llm-attacks or DeepInception? llm-attacks: Dormant. DeepInception: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for llm-attacks and DeepInception? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [llm-attacks trust report](/tools/llm-attacks-llm-attacks/trust); [DeepInception trust report](/tools/tmlr-group-deepinception/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=llm-attacks-llm-attacks`](/api/graphcanon/graph?tool=llm-attacks-llm-attacks) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_