Idle Scan 的起源

antirez 899 days ago. 119816 views.

The Idle scan was conceived at the end of 1998, evidenced by emails. I had moved to Milan a few months prior, having been there since September if I recall correctly, brimming with new ideas, unaware that my stay in that city would be brief. I spent the summer on the beaches of Sicily, mainly occupied with reading many books recommended by the folks at Seclab (mostly by David). However, those readings needed a catalyst: the Idle scan was an attack born from theoretical rumination, but the stream of thoughts originated from a rather practical circumstance. I had recently created Hping, a tool whose logo was borrowed from that of Nutella. I mention this to emphasize the seriousness that governed my efforts at that time — after all, I was only twenty-one and already in Northern Italy with a full-time job on my shoulders; some understanding was warranted.

Hping was a Swiss Army knife for the TCP/IP protocol. Its initial use was mostly exploratory, for research. With Hping, you could assemble TCP, UDP, and ICMP packets in the most bizarre manner, and encapsulate them in equally eccentric IP packets, fragmented, with fields set to anomalous values. These packets were sent around to observe the network stack response of different operating systems.

This is where Idle scan originates: playing with Hping for just a few minutes revealed a well-known yet (to me) surprising fact. The response packets had an ID field that continuously incremented by some measure. At that time, given that the attacks I would later disclose were not yet known, this ID field behavior aroused no concern. Every time an operating system emitted an IP packet, it first incremented a counter (which reset to zero once it reached the maximum value of two to the sixteenth power minus one), then the packet was sent with the ID set to the counter's value. The counter was universal for all outgoing packets. This allowed, for starters, to estimate the outgoing traffic of any networked computer. This information leak struck me; I saw it as a concerning anomaly. I wrote an initial post on BUGTRAQ, highlighting the issue. Among the responses was one from an Internet luminary, someone who had drafted central RFCs for the TCP/IP protocol. He said that, yes, they were aware; it was a well-known fact. In short: although this characteristic could be used for traffic estimation, most saw no risk. And resolving that issue, deemed negligible, would require a significant overhaul of operating systems. Not worth it.

But I was losing sleep over it, hardly a secondary issue to me. I was convinced that the information provided by the incrementing ID field could be combined with other elements (which I had not fully grasped yet) to mount a far more serious attack. I discussed it with Lorenzo Cavallaro. Lorenzo had introduced me to raw socket techniques months earlier, which I had used to write Hping. He had become my go-to conversational partner, as well as a dear friend; if I had to ponder on TCP/IP-related matters, I would discuss them with him. When I told him about these new ideas, I had to be vague, not by choice but because I hadn't yet pieced together the final attack. Despite my vagueness, he appeared fairly interested.

A couple of days later, I spoke to him again. Finally, I managed to give him a more comprehensive description of the Idle scan (not yet named as such). I had reasoned it out on paper, as there was no way to test it practically. If I remember correctly, Hping was missing some of the necessary functions, although I wouldn't bet on this part: it's been twenty-five years. My memory clears as I write. I believe you couldn't choose the exact flags of the outgoing TCP packet. Anyway, from what I remember, the modifications to Hping took little time, so we were able to test my theory in practice as well. The Idle scan really worked, and proving it in real conditions was very exciting. I don't remember who made this parallel, but essentially, it was like observing the movement of an invisible celestial body indirectly, measuring only its gravitational effects on another, more easily observable body, much like the discovery of Pluto.

All that was left was to make the attack public. Unfortunately, the thought of writing a lengthy email in English terrified me. I was aware that the Idle scan was an interesting idea, and precisely because of that, I was afraid of botching its announcement due to poor presentation. After all, the attack was cumbersome; it could even end up being described so poorly as to make it incomprehensible. Lorenzo and I wrote that email late at night, at my place, certainly drunk. Better than writing it alone; Lorenzo's English, even if slightly, was better than mine. It happened that a colleague from Seclab (also one of the founders), whom I consider a true genius in information security, came from a family of restaurateurs from Emilia. One evening he shows up at my place with a bag. Inside the bag is a fine piece of grey mullet roe, which I had never seen, let alone tasted (it would become one of my favorite foods). The cook-hacker prepares pasta for all of us, and together we eat and drink sufficiently. At the end of the evening, the others leave (there was someone else, besides the cook-hacker), but Lorenzo stays a bit longer.

That evening, Lorenzo and I, fairly tipsy, recklessly thought the time had come to write the Idle scan announcement email (still preserved in the BUGTRAQ archives, and which today appears genuinely delirious [1]). We sit down at my PC to work. The email opens like this: I have uncovered a new tcp port scan method. Instead all others it allows you to scan using spoofed packets, so scanned hosts can't see your real address. Not just the grammar, even the peremptory tone of the email is utterly inappropriate. To top it off, we propose calling the attack dumb host scan, but fortunately, someone quickly finds a better name, which became the official one: Idle scan. Long story short, despite its flawed origins, the Idle scan has become a classic attack, and it's safe to say, as is often the case, that the rest is history.

[1] https://seclists.org/bugtraq/1998/Dec/79

blog comments powered by Disqus