Hongwei Wang, Yongfeng Zhang, Kai Mei, Zhenting Wang, Hanrong Zhang, Jingyuan Huang, Yifei Yao, Chenlu Zhan
4 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 2 failures of our instrument; 9 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.02644.json · badge: /api/ran/2410.02644.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| agiresearch/ASB | canonical (classifier label) classifier basis: census |
4 ran · 9 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| calculate_perplexities | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
agiresearch/ASB/memory_defense/threshold.py code served (permissive licence) · get_code("760fb2e1fce9b7b1") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| check_attack_success | Ran ran, violated the contract we drafted |
agiresearch/ASB/main_attacker.py code served (permissive licence) · get_code("5dad87aa78c56e1b") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| check_original_success | Ran ran, violated the contract we drafted |
agiresearch/ASB/main_attacker.py code served (permissive licence) · get_code("c3e3e3bfd5b68ace") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| parse_plans | Ran ran; our contract draft was wrong, not the code |
agiresearch/ASB/memory_defense/threshold.py code served (permissive licence) · get_code("becaa275502d6a0e") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| evaluate_plans | Not yet run unverified (harvested, no recorded run) |
agiresearch/ASB/memory_defense/llm_dection.py code served (permissive licence) · get_code("85a853d1af0b8444") How it ranno invocation recorded. |
| evaluate_plans | Not yet run unverified (harvested, no recorded run) |
agiresearch/ASB/memory_defense/llm_utils.py code served (permissive licence) · get_code("708307030e0e3198") How it ranno invocation recorded. |
| judge_response | Not yet run unverified (harvested, no recorded run) |
agiresearch/ASB/main_attacker.py code served (permissive licence) · get_code("0c3b4891805a8262") How it ranno invocation recorded. |
| load_model_and_tokenizer | Not yet run unverified (harvested, no recorded run) |
agiresearch/ASB/memory_defense/ppl_utils.py code served (permissive licence) · get_code("faabedfe90d4f114") How it ranno invocation recorded. |
| ppl_evaluate_workflow | Not yet run unverified (harvested, no recorded run) |
agiresearch/ASB/memory_defense/ppl_utils.py code served (permissive licence) · get_code("64a56135a35ae0d4") How it ranno invocation recorded. |
| process_log_clean | Not yet run unverified (harvested, no recorded run) |
agiresearch/ASB/memory_defense/llm_dection.py code served (permissive licence) · get_code("441fac1bb4bb4dab") How it ranno invocation recorded. |
| process_log_clean | Not yet run unverified (harvested, no recorded run) |
agiresearch/ASB/memory_defense/ppl_dection.py code served (permissive licence) · get_code("d1d83916b0534aaf") How it ranno invocation recorded. |
| process_log_clean | Not yet run unverified (harvested, no recorded run) |
agiresearch/ASB/memory_defense/threshold.py code served (permissive licence) · get_code("44b5653b885b98ee") How it ranno invocation recorded. |
| process_log_memory | Not yet run unverified (harvested, no recorded run) |
agiresearch/ASB/memory_defense/llm_dection.py code served (permissive licence) · get_code("33f024008fa1f944") How it ranno invocation recorded. |
Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 13 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature does not comprehensively evaluate attacks and defenses against LLMbased agents. To address this, we introduce Agent Security Bench (ASB), a comprehensive framework designed to formalize, benchmark, and evaluate the attacks and defenses of LLM-based agents, including 10 scenarios (e.g., e-commerce, autonomous driving, finance), 10 agents targeting the scenarios, over 400 tools, 27 different types of attack/defense methods, and 7 evaluation metrics. Based on ASB, we benchmark 10 prompt injection attacks, a memory poisoning attack, a novel Plan-of-Thought backdoor attack, 4 mixed attacks, and 11 corresponding defenses across 13 LLM backbones. Our benchmark results reveal critical vulnerabilities in different stages of agent operation, including system prompt, user prompt handling, tool usage, and memory retrieval, with the highest average attack success rate of 84.30%, but limited effectiveness shown in current defenses, unveiling important works to be done in terms of agent security for the community. We also introduce a new metric to evaluate the agents' capability to balance utility and security. Our code can be found at https: //github.com/agiresearch/ASB. Furthermore, ASB explores the vulnerabilities in agents performing tasks in diverse settings. Specifically, ASB evaluates across 10 task scenarios, 10 corresponding agents, and over 400 tools, including both normal and attack tools, and 400 tasks, divided into aggressive and non-aggressive types. The aggressive tasks assess the agent's refusal rate in response to risky or aggressive instructions. Our key contributions are summarized as follows: ① We design and develop Agent Security Bench (ASB), the first comprehensive benchmark including 10 scenarios (e.g., e-commerce, autonomous driving, finance), 10 agents targeting the scenarios, over 400 tools and tasks for evaluating the security of LLM-based agents against numerous attacks and defense strategies. ② We propose a novel PoT Backdoor Attack, which embeds hidden instructions into the system prompt, exploiting the agent's planning process to achieve high attack success rates. ③ We formalize and categorize various adversarial threats targeting key components of LLM agents, including DPI, IPI, Memory Poisoning Attacks, PoT Backdoor Attacks, and Mixed Attacks, covering vulnerabilities in system prompt definition, user prompt handling, memory retrieval, and tool usage. ④ We benchmark 27 different types of attacks and defenses on ASB across 13 LLM backbones with 7 metrics, demonstrating that LLM-based agents are vulnerable to the attacks, with the highest average attack success rates exceeding 84.30%. In contrast, existing defenses are often ineffective. Our work highlights the need for stronger defenses to protect LLM agents from sophisticated adversarial techniques. ⑤ We introduce the Net Resilient Performance (NRP) metric to assess the agents' balance between utility and security and emphasize the importance of performance testing on ASB for selecting suitable backbones for agent applications.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2410.02644")
get_code_for_paper("2410.02644")
have("2410.02644")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2410.02644.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2410.02644)
Connect an agent — have() is free.