arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.20446cs.CR
收藏

理解网络安全竞赛中的人机协作

Understanding Human-AI Collaboration in Cybersecurity Competitions

William & Mary(威廉与玛丽学院);IBM Research(IBM研究院)

Tingxuan Tang, Nicolas Janis, Kalyn Asher Montague, Kevin Eykholt, Dhilung Kirat, Youngja Park, Jiyong Jang, Adwait Nadkarni, Yue Xiao

AI总结:

研究探讨了网络安全竞赛中人类与AI协作的有效性,发现AI代理在自主引导提示和工具使用时能超越多数人类团队。

摘要:

夺旗竞赛(CTF)正逐渐成为评估AI在解决安全任务方面能力的测试场,这归因于其受控环境和客观成功标准。现有的评估主要集中在AI在脱离人类CTF参赛者的情况下解决CTF挑战的成效。随着AI在学术和工业中的使用增加,人类玩家可能与AI代理协作解决挑战的可能性也日益增加。这种可能性揭示了一个关键的知识空白:人类如何感知AI的CTF帮助;当提供帮助时,他们如何协作,这种协作是否有效,与人类表现相比如何;受AI帮助的人类在相同挑战上的表现如何与完全自主的AI代理相比较。我们通过首次对AI帮助进行现场、实地CTF的实证研究来填补这一空白。在41名参与者的研究中,我们定性地研究了(i)参与者在使用AI之前和之后感知、信任和期望的变化,以及(ii)参与者如何与一个仪器化的AI代理协作。此外,我们还(iii)在相同的新挑战集上对四个自主AI代理进行基准测试,以比较与人类团队的结果,并分析代理轨迹。我们发现,随着比赛的进行,团队越来越倾向于将更大的子任务委托给AI,赋予其更多自主权。有趣的是,CTF挑战的解决率往往受模型推理能力的限制,而不是人类玩家:无效的提示和糟糕的上下文指定成为主要瓶颈。令人惊讶的是,能够自主指导其提示和工具使用的自主代理 bypass 这个瓶颈,并超越大多数人类团队,最终在比赛中排名第二。我们最后得出关于未来CTF挑战设计以及构建有效的人机协作AI系统在安全领域的启示。

英文摘要:

Capture-the-Flag (CTF) competitions are increasingly becoming a testbed for evaluating AI capabilities at solving security tasks, due to the controlled environments and objective success criteria. Existing evaluations have focused on how successful AI is at solving CTF challenges in isolation from human CTF players. As AI usage increases in both academic and industrial settings, it is equally likely that human players may collaborate with AI agents to solve challenges. This possibility exposes a key knowledge gap: how do humans perceive AI CTF assistance; when assistance is provided, how do they collaborate and is it effective with respect to human performance; how do humans assisted by AI compare to the performance of fully autonomous AI agents on the same challenges. We address this gap with the first empirical study of AI assistance in a live, onsite CTF. In a study with 41 participants, we qualitatively study (i) how participants' perception, trust, and expectations shift before versus after hands-on AI use, and (ii) how participants collaborate with an instrumented AI agent. Moreover, we also (iii) benchmark four autonomous AI agents on the same fresh challenge set to compare outcomes with human teams and analyze agent trajectories. We find that, as the competition progresses, teams increasingly delegate larger subtasks to the AI, giving it more agency. Interestingly, CTF challenges solving rates are often constrained not by model's reasoning capabilities, but rather by the human players: ineffective prompting and poor context specification become the primary bottleneck. Remarkably, autonomous agents that self-direct their prompting and tool use bypass this bottleneck and outperform most human teams, coming in second overall in the competition. We conclude with implications for the future design of CTF challenges and for building effective human-in-the-loop AI systems for security.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑