From 07778c2ddbd5a1caf67ba2270cf075a001cfd740 Mon Sep 17 00:00:00 2001 From: shiva108 Date: Tue, 3 Feb 2026 18:09:16 +0100 Subject: [PATCH] docs: add arXiv links to seminal papers and correct a publication year. --- docs/Chapter_07_Lab_Setup_and_Environmental_Safety.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/Chapter_07_Lab_Setup_and_Environmental_Safety.md b/docs/Chapter_07_Lab_Setup_and_Environmental_Safety.md index 463050f..7a75f00 100644 --- a/docs/Chapter_07_Lab_Setup_and_Environmental_Safety.md +++ b/docs/Chapter_07_Lab_Setup_and_Environmental_Safety.md @@ -1079,11 +1079,11 @@ This setup allows testing **"Indirect Prompt Injection"**, where the Attacker po ### Seminal Papers -| Paper | Year | Contribution | -| :------------------------------------------- | :--- | :------------------------------------------------------------------------------------------------------------------------------ | -| **"LLMSmith: A Tool for Investigating RCE"** | 2024 | Demonstrated "Code Escape" where prompt injection leads to Remote Code Execution in LLM frameworks [1]. | -| **"Whisper Leak: Side-channel attacks"** | 2025 | Showed how network traffic patterns (packet size/timing) can leak the topic of LLM prompts even over encrypted connections [2]. | -| **"SandboxEval"** | 2025 | Introduced a benchmark for evaluating the security of sandboxes against code generated by LLMs [3]. | +| Paper | Year | Contribution | +| :--------------------------------------------------------------------------- | :--- | :------------------------------------------------------------------------------------------------------------------------------ | +| **["Demystifying RCE (LLMSmith)"](https://arxiv.org/abs/2309.02926)** | 2024 | Demonstrated "Code Escape" where prompt injection leads to Remote Code Execution in LLM frameworks [1]. | +| **["Whisper Leak: Side-channel attacks"](https://arxiv.org/abs/2511.03675)** | 2024 | Showed how network traffic patterns (packet size/timing) can leak the topic of LLM prompts even over encrypted connections [2]. | +| **["SandboxEval"](https://arxiv.org/abs/2504.00018)** | 2025 | Introduced a benchmark for evaluating the security of sandboxes against code generated by LLMs [3]. | ### Current Research Gaps